{"rows":[{"split":"full","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":151,"tasks":151,"splitTasks":152,"passes":52,"passRate":0.34210526315789475,"avgScore":0.5925587020443251,"totalDurationS":526557.0650000001,"totalInputTokens":510255691,"totalOutputTokens":5770631,"totalCostUsd":947.52,"costSource":"official"},{"split":"full","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":151,"tasks":151,"splitTasks":152,"passes":49,"passRate":0.3223684210526316,"avgScore":0.5829341986297972,"totalDurationS":346975.83300000016,"totalInputTokens":478752169,"totalOutputTokens":4189738,"totalCostUsd":820.35,"costSource":"official"},{"split":"full","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":151,"tasks":151,"splitTasks":152,"passes":48,"passRate":0.3157894736842105,"avgScore":0.5777997716313646,"totalDurationS":325797.8419999999,"totalInputTokens":420284625,"totalOutputTokens":3374771,"totalCostUsd":705.22,"costSource":"official"},{"split":"full","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":151,"tasks":151,"splitTasks":152,"passes":49,"passRate":0.3223684210526316,"avgScore":0.5762070581232449,"totalDurationS":261692.78100000005,"totalInputTokens":407254514,"totalOutputTokens":2433429,"totalCostUsd":623.9,"costSource":"official"},{"split":"full","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":148,"tasks":148,"splitTasks":152,"passes":49,"passRate":0.3223684210526316,"avgScore":0.5575758972199165,"totalDurationS":290234.9759999998,"totalInputTokens":2130923906,"totalOutputTokens":11823598,"totalCostUsd":428.09,"costSource":"official"},{"split":"full","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":151,"tasks":151,"splitTasks":152,"passes":46,"passRate":0.3026315789473684,"avgScore":0.5552936329794441,"totalDurationS":573533.894,"totalInputTokens":2477096511,"totalOutputTokens":15655260,"totalCostUsd":2278.49,"costSource":"official"},{"split":"full","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":148,"tasks":148,"splitTasks":152,"passes":45,"passRate":0.29605263157894735,"avgScore":0.5527655474845958,"totalDurationS":271985.12600000005,"totalInputTokens":2031030687,"totalOutputTokens":11283650,"totalCostUsd":408.58,"costSource":"official"},{"split":"full","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":149,"tasks":149,"splitTasks":152,"passes":48,"passRate":0.3157894736842105,"avgScore":0.5520199630375696,"totalDurationS":462563.7839999999,"totalInputTokens":1792169341,"totalOutputTokens":10118922,"totalCostUsd":1637.91,"costSource":"official"},{"split":"full","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":151,"tasks":151,"splitTasks":152,"passes":43,"passRate":0.28289473684210525,"avgScore":0.5437948986344553,"totalDurationS":223867.21800000002,"totalInputTokens":527143796,"totalOutputTokens":1656404,"totalCostUsd":696.97,"costSource":"official"},{"split":"full","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":301,"tasks":152,"splitTasks":152,"passes":93,"passRate":0.3059210526315789,"avgScore":0.5361628463309976,"totalDurationS":340729.69649999996,"totalInputTokens":762936773.1666666,"totalOutputTokens":3798417.8333333335,"totalCostUsd":771.62,"costSource":"db+list"},{"split":"full","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":151,"tasks":151,"splitTasks":152,"passes":45,"passRate":0.29605263157894735,"avgScore":0.5339594263114672,"totalDurationS":236298.854,"totalInputTokens":312003435,"totalOutputTokens":1602933,"totalCostUsd":467.03,"costSource":"official"},{"split":"full","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":150,"tasks":150,"splitTasks":152,"passes":44,"passRate":0.2894736842105263,"avgScore":0.5302736569925712,"totalDurationS":402228.2569999999,"totalInputTokens":1344833416,"totalOutputTokens":6334961,"totalCostUsd":1193.47,"costSource":"official"},{"split":"full","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":307,"tasks":152,"splitTasks":152,"passes":89,"passRate":0.29605263157894735,"avgScore":0.5276278004520454,"totalDurationS":373587.878,"totalInputTokens":1095236840.8333333,"totalOutputTokens":5443524.666666667,"totalCostUsd":1084.09,"costSource":"db+list"},{"split":"full","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":148,"tasks":148,"splitTasks":152,"passes":47,"passRate":0.3092105263157895,"avgScore":0.5267408894394475,"totalDurationS":560523.619,"totalInputTokens":2444275652,"totalOutputTokens":14923513,"totalCostUsd":2302.08,"costSource":"official"},{"split":"full","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":148,"tasks":148,"splitTasks":152,"passes":41,"passRate":0.26973684210526316,"avgScore":0.5248561340297907,"totalDurationS":729633.2999999999,"totalInputTokens":1234201310,"totalOutputTokens":12430863,"totalCostUsd":486.47,"costSource":"db"},{"split":"full","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":299,"tasks":152,"splitTasks":152,"passes":91,"passRate":0.3059210526315789,"avgScore":0.523728673169988,"totalDurationS":340491.97,"totalInputTokens":594028867,"totalOutputTokens":2890301.5,"totalCostUsd":575.68,"costSource":"db+list"},{"split":"full","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":302,"tasks":152,"splitTasks":152,"passes":87,"passRate":0.29495614035087714,"avgScore":0.5210026942935828,"totalDurationS":328693.94200000004,"totalInputTokens":539877934.6666666,"totalOutputTokens":2196349.5,"totalCostUsd":518.72,"costSource":"db+list"},{"split":"full","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":150,"tasks":150,"splitTasks":152,"passes":42,"passRate":0.27631578947368424,"avgScore":0.5190143852885959,"totalDurationS":435722.7299999999,"totalInputTokens":1003034490,"totalOutputTokens":4151470,"totalCostUsd":917.87,"costSource":"official"},{"split":"full","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":149,"tasks":149,"splitTasks":152,"passes":43,"passRate":0.28289473684210525,"avgScore":0.515832318778052,"totalDurationS":669880.985,"totalInputTokens":1402173402,"totalOutputTokens":7479641,"totalCostUsd":605.78,"costSource":"db"},{"split":"full","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":151,"tasks":151,"splitTasks":152,"passes":41,"passRate":0.26973684210526316,"avgScore":0.5122184380800093,"totalDurationS":320860.16600000014,"totalInputTokens":668267258,"totalOutputTokens":5447367,"totalCostUsd":336.79,"costSource":"db"},{"split":"full","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":149,"tasks":149,"splitTasks":152,"passes":41,"passRate":0.26973684210526316,"avgScore":0.5072487812208666,"totalDurationS":775905.225,"totalInputTokens":950614474,"totalOutputTokens":7394400,"totalCostUsd":463.87,"costSource":"db"},{"split":"full","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":297,"tasks":152,"splitTasks":152,"passes":82,"passRate":0.27960526315789475,"avgScore":0.5070206498203882,"totalDurationS":427119,"totalInputTokens":1244130625.6666667,"totalOutputTokens":5783219.833333333,"totalCostUsd":544.61,"costSource":"list"},{"split":"full","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":149,"tasks":149,"splitTasks":152,"passes":44,"passRate":0.2894736842105263,"avgScore":0.5037352082410917,"totalDurationS":239192,"totalInputTokens":2499272937,"totalOutputTokens":6752715,"totalCostUsd":390.61,"costSource":"list"},{"split":"full","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":152,"tasks":152,"splitTasks":152,"passes":46,"passRate":0.3026315789473684,"avgScore":0.49414814826021464,"totalDurationS":238042,"totalInputTokens":1435261861,"totalOutputTokens":4162374,"totalCostUsd":235.12,"costSource":"list"},{"split":"full","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":150,"tasks":150,"splitTasks":152,"passes":39,"passRate":0.2565789473684211,"avgScore":0.4870141224330407,"totalDurationS":251985,"totalInputTokens":2740460142,"totalOutputTokens":10436301,"totalCostUsd":4340.24,"costSource":"official"},{"split":"full","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":299,"tasks":152,"splitTasks":152,"passes":82,"passRate":0.27631578947368424,"avgScore":0.484942264470657,"totalDurationS":314395.5,"totalInputTokens":822499178,"totalOutputTokens":3817073,"totalCostUsd":380.73,"costSource":"list"},{"split":"full","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":299,"tasks":152,"splitTasks":152,"passes":80,"passRate":0.26644736842105265,"avgScore":0.47931391024591824,"totalDurationS":349652.5,"totalInputTokens":560480756,"totalOutputTokens":6366308.5,"totalCostUsd":601.69,"costSource":"db"},{"split":"full","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":298,"tasks":151,"splitTasks":152,"passes":77,"passRate":0.2598684210526316,"avgScore":0.465716312064728,"totalDurationS":354908.11950000003,"totalInputTokens":533875323.5,"totalOutputTokens":2793979.5,"totalCostUsd":261.53,"costSource":"db+list"},{"split":"full","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":152,"tasks":152,"splitTasks":152,"passes":37,"passRate":0.24342105263157895,"avgScore":0.46128766882143674,"totalDurationS":165192,"totalInputTokens":699354083,"totalOutputTokens":2559522,"totalCostUsd":127.52,"costSource":"list"},{"split":"full","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":145,"tasks":145,"splitTasks":152,"passes":35,"passRate":0.23026315789473684,"avgScore":0.4578443243363864,"totalDurationS":128044.22844149194,"totalInputTokens":334305043,"totalOutputTokens":2340693,"totalCostUsd":309.77,"costSource":"db"},{"split":"full","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":150,"tasks":150,"splitTasks":152,"passes":41,"passRate":0.26973684210526316,"avgScore":0.4514857743894153,"totalDurationS":645508,"totalInputTokens":1692408720,"totalOutputTokens":22067608,"totalCostUsd":3985,"costSource":"published+task-ratio"},{"split":"full","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":299,"tasks":151,"splitTasks":152,"passes":73,"passRate":0.2390350877192982,"avgScore":0.4509751802373446,"totalDurationS":270652.0256666667,"totalInputTokens":251962276.66666666,"totalOutputTokens":1269048.8333333333,"totalCostUsd":248.12,"costSource":"db+list"},{"split":"full","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":438,"tasks":152,"splitTasks":152,"passes":110,"passRate":0.2445175438596491,"avgScore":0.44715784362305094,"totalDurationS":270900.40022482676,"totalInputTokens":489884949,"totalOutputTokens":3517360.8333333335,"totalCostUsd":415.59,"costSource":"db+list"},{"split":"full","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":148,"tasks":148,"splitTasks":152,"passes":31,"passRate":0.20394736842105263,"avgScore":0.428847508157024,"totalDurationS":1000718.9020000002,"totalInputTokens":2742661908,"totalOutputTokens":14977273,"totalCostUsd":null,"costSource":null},{"split":"full","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":297,"tasks":152,"splitTasks":152,"passes":69,"passRate":0.22697368421052633,"avgScore":0.4258635230185982,"totalDurationS":310012.218,"totalInputTokens":244642169.5,"totalOutputTokens":1565131.5,"totalCostUsd":128.23,"costSource":"db+list"},{"split":"full","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":137,"tasks":137,"splitTasks":152,"passes":32,"passRate":0.21052631578947367,"avgScore":0.42487183710893694,"totalDurationS":229732.552303883,"totalInputTokens":429515271,"totalOutputTokens":4464514,"totalCostUsd":1899.32,"costSource":"official+adj"},{"split":"full","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":151,"tasks":151,"splitTasks":152,"passes":34,"passRate":0.2236842105263158,"avgScore":0.4234878390395742,"totalDurationS":519320,"totalInputTokens":1209502455,"totalOutputTokens":16507476,"totalCostUsd":2815,"costSource":"published+task-ratio"},{"split":"full","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":136,"tasks":136,"splitTasks":152,"passes":33,"passRate":0.21710526315789475,"avgScore":0.42072396960513175,"totalDurationS":297468.11566528457,"totalInputTokens":469259907,"totalOutputTokens":3279175,"totalCostUsd":446.52,"costSource":"db"},{"split":"full","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":152,"tasks":144,"splitTasks":152,"passes":35,"passRate":0.2236842105263158,"avgScore":0.412877641079695,"totalDurationS":382422.5,"totalInputTokens":880037048.5,"totalOutputTokens":9436038.5,"totalCostUsd":2314.73,"costSource":"official"},{"split":"full","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":146,"tasks":143,"splitTasks":152,"passes":30,"passRate":0.19078947368421054,"avgScore":0.4113172272326027,"totalDurationS":558819.5,"totalInputTokens":1903250155.5,"totalOutputTokens":8006212,"totalCostUsd":935.7,"costSource":"db"},{"split":"full","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":146,"tasks":146,"splitTasks":152,"passes":31,"passRate":0.20394736842105263,"avgScore":0.41085406808572505,"totalDurationS":387747,"totalInputTokens":1291344387,"totalOutputTokens":7729473,"totalCostUsd":1085.62,"costSource":"db"},{"split":"full","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":142,"tasks":139,"splitTasks":152,"passes":33,"passRate":0.2138157894736842,"avgScore":0.40680078557980925,"totalDurationS":211627.30808669614,"totalInputTokens":148061075,"totalOutputTokens":1687764,"totalCostUsd":173.52,"costSource":"list"},{"split":"full","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":143,"tasks":143,"splitTasks":152,"passes":34,"passRate":0.2236842105263158,"avgScore":0.40677645580102734,"totalDurationS":298162,"totalInputTokens":1796865182,"totalOutputTokens":6432918,"totalCostUsd":1626,"costSource":"published+task-ratio"},{"split":"full","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":143,"tasks":143,"splitTasks":152,"passes":28,"passRate":0.18421052631578946,"avgScore":0.4049605336355299,"totalDurationS":279527.28043104644,"totalInputTokens":1342066095,"totalOutputTokens":5568247,"totalCostUsd":1132.24,"costSource":"official"},{"split":"full","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":300,"tasks":152,"splitTasks":152,"passes":60,"passRate":0.20394736842105263,"avgScore":0.4024908249653849,"totalDurationS":275061.747,"totalInputTokens":171679764,"totalOutputTokens":1124088.5,"totalCostUsd":89.49,"costSource":"db+list"},{"split":"full","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":149,"tasks":149,"splitTasks":152,"passes":28,"passRate":0.18421052631578946,"avgScore":0.39776664940409484,"totalDurationS":270641,"totalInputTokens":294404262,"totalOutputTokens":2853487,"totalCostUsd":357.68,"costSource":"db"},{"split":"full","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":138,"tasks":138,"splitTasks":152,"passes":31,"passRate":0.20394736842105263,"avgScore":0.39480863219234935,"totalDurationS":280094,"totalInputTokens":338804815,"totalOutputTokens":2898338,"totalCostUsd":176.65,"costSource":"db+list"},{"split":"full","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":139,"tasks":137,"splitTasks":152,"passes":30,"passRate":0.19736842105263158,"avgScore":0.3924651258147475,"totalDurationS":229751.49587275658,"totalInputTokens":234782616,"totalOutputTokens":2196372,"totalCostUsd":242.24,"costSource":"list"},{"split":"full","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":152,"tasks":152,"splitTasks":152,"passes":26,"passRate":0.17105263157894737,"avgScore":0.3850041500197,"totalDurationS":151697,"totalInputTokens":287164350,"totalOutputTokens":1082713,"totalCostUsd":57,"costSource":"list"},{"split":"full","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":141,"tasks":141,"splitTasks":152,"passes":25,"passRate":0.16447368421052633,"avgScore":0.38312084275574215,"totalDurationS":489984,"totalInputTokens":452042179,"totalOutputTokens":3793251,"totalCostUsd":1837.79,"costSource":"official+adj"},{"split":"full","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":179,"tasks":142,"splitTasks":152,"passes":40,"passRate":0.2050438596491228,"avgScore":0.3732607831603129,"totalDurationS":459960.9185098016,"totalInputTokens":488753872.1666667,"totalOutputTokens":7283825.166666667,"totalCostUsd":274.1,"costSource":"db"},{"split":"full","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":152,"tasks":152,"splitTasks":152,"passes":26,"passRate":0.17105263157894737,"avgScore":0.3636965114654929,"totalDurationS":139211,"totalInputTokens":109294354,"totalOutputTokens":1270291,"totalCostUsd":146.61,"costSource":"db"},{"split":"full","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":137,"tasks":137,"splitTasks":152,"passes":21,"passRate":0.13815789473684212,"avgScore":0.35803700118782017,"totalDurationS":153370.83306965837,"totalInputTokens":456438963,"totalOutputTokens":3700468,"totalCostUsd":1792.72,"costSource":"official+adj"},{"split":"full","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":142,"tasks":141,"splitTasks":152,"passes":24,"passRate":0.15789473684210525,"avgScore":0.3521506822590183,"totalDurationS":446984.7452694551,"totalInputTokens":807329919,"totalOutputTokens":3963995.5,"totalCostUsd":1688.85,"costSource":"official+adj"},{"split":"full","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":142,"tasks":142,"splitTasks":152,"passes":25,"passRate":0.16447368421052633,"avgScore":0.3270766092627965,"totalDurationS":332449,"totalInputTokens":1212565963,"totalOutputTokens":3542216,"totalCostUsd":2018.05,"costSource":"db+list+adj"},{"split":"full","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":144,"tasks":144,"splitTasks":152,"passes":19,"passRate":0.125,"avgScore":0.3172013766706849,"totalDurationS":685102,"totalInputTokens":1673959024,"totalOutputTokens":20768691,"totalCostUsd":439.63,"costSource":"db"},{"split":"full","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":105,"tasks":99,"splitTasks":152,"passes":22,"passRate":0.13486842105263158,"avgScore":0.31695780433940046,"totalDurationS":101780.76887404779,"totalInputTokens":352060264.5,"totalOutputTokens":2726292,"totalCostUsd":1356.25,"costSource":"official+adj"},{"split":"full","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":142,"tasks":142,"splitTasks":152,"passes":18,"passRate":0.11842105263157894,"avgScore":0.3156864509879294,"totalDurationS":363579,"totalInputTokens":1382717830,"totalOutputTokens":17557559,"totalCostUsd":663.87,"costSource":"db+list"},{"split":"full","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":152,"tasks":152,"splitTasks":152,"passes":18,"passRate":0.11842105263157894,"avgScore":0.31023834901975544,"totalDurationS":88490,"totalInputTokens":119921277,"totalOutputTokens":610291,"totalCostUsd":26.77,"costSource":"list"},{"split":"full","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":149,"tasks":141,"splitTasks":152,"passes":22,"passRate":0.14144736842105263,"avgScore":0.2927265620525372,"totalDurationS":529548.719956005,"totalInputTokens":3369212141,"totalOutputTokens":3653426,"totalCostUsd":2968.62,"costSource":"db+adj"},{"split":"full","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":143,"tasks":143,"splitTasks":152,"passes":18,"passRate":0.11842105263157894,"avgScore":0.2863832387982169,"totalDurationS":199675.9292053005,"totalInputTokens":1070761845,"totalOutputTokens":2049232,"totalCostUsd":335.05,"costSource":"db"},{"split":"full","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":260,"tasks":140,"splitTasks":152,"passes":35,"passRate":0.11513157894736842,"avgScore":0.2813736456137783,"totalDurationS":607138.4432532396,"totalInputTokens":755773178.3333334,"totalOutputTokens":5896205,"totalCostUsd":439.78,"costSource":"db+list"},{"split":"full","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":275,"tasks":146,"splitTasks":152,"passes":39,"passRate":0.12390350877192982,"avgScore":0.2762014846817647,"totalDurationS":470844.49271820637,"totalInputTokens":511717582.8333333,"totalOutputTokens":4746342.166666667,"totalCostUsd":273.05,"costSource":"db"},{"split":"full","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":272,"tasks":146,"splitTasks":152,"passes":25,"passRate":0.08552631578947369,"avgScore":0.24606981345822615,"totalDurationS":484970.8091920079,"totalInputTokens":738910364.1666666,"totalOutputTokens":7027388.333333333,"totalCostUsd":253.85,"costSource":"db"},{"split":"full","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":261,"tasks":146,"splitTasks":152,"passes":25,"passRate":0.08552631578947369,"avgScore":0.23555956574853623,"totalDurationS":386539.2838370383,"totalInputTokens":394850494.1666667,"totalOutputTokens":4001432.3333333335,"totalCostUsd":43.34,"costSource":"db+list"},{"split":"full","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":241,"tasks":144,"splitTasks":152,"passes":25,"passRate":0.09210526315789473,"avgScore":0.21665039689683385,"totalDurationS":659868.3114792772,"totalInputTokens":295931464.5,"totalOutputTokens":6043559,"totalCostUsd":123.45,"costSource":"db+list"},{"split":"full","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":149,"tasks":142,"splitTasks":152,"passes":11,"passRate":0.07236842105263158,"avgScore":0.21253888440188418,"totalDurationS":155198.84874021716,"totalInputTokens":223145635.66666666,"totalOutputTokens":2267515.6666666665,"totalCostUsd":284.6,"costSource":"list"},{"split":"full","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":262,"tasks":145,"splitTasks":152,"passes":13,"passRate":0.04276315789473684,"avgScore":0.1577879873494589,"totalDurationS":284644.0846058948,"totalInputTokens":168652811,"totalOutputTokens":2745183,"totalCostUsd":80.18,"costSource":"db+list"},{"split":"full","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":223,"tasks":146,"splitTasks":152,"passes":14,"passRate":0.05921052631578947,"avgScore":0.14187993275125252,"totalDurationS":520646.2217991107,"totalInputTokens":277209591.6666667,"totalOutputTokens":4379146.166666667,"totalCostUsd":26.74,"costSource":"db+list"},{"split":"full","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":144,"tasks":142,"splitTasks":152,"passes":11,"passRate":0.07236842105263158,"avgScore":0.133367903588527,"totalDurationS":147936.49156970065,"totalInputTokens":206835017.5,"totalOutputTokens":3239534.5,"totalCostUsd":134.93,"costSource":"db"},{"split":"full","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":143,"tasks":140,"splitTasks":152,"passes":7,"passRate":0.046052631578947366,"avgScore":0.1261454861416316,"totalDurationS":65674.81911909918,"totalInputTokens":55532219.5,"totalOutputTokens":512410,"totalCostUsd":174.28,"costSource":"db"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":55,"tasks":55,"splitTasks":55,"passes":17,"passRate":0.3090909090909091,"avgScore":0.518289251030242,"totalDurationS":161212.698,"totalInputTokens":121977813,"totalOutputTokens":1724941,"totalCostUsd":251.84,"costSource":"official"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":55,"tasks":55,"splitTasks":55,"passes":16,"passRate":0.2909090909090909,"avgScore":0.4998323694894931,"totalDurationS":81806.452,"totalInputTokens":79809670,"totalOutputTokens":693664,"totalCostUsd":141.33,"costSource":"official"},{"split":"full/full-spectrum","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":54,"tasks":54,"splitTasks":55,"passes":16,"passRate":0.2909090909090909,"avgScore":0.4987405398972178,"totalDurationS":200627.39300000004,"totalInputTokens":465363592,"totalOutputTokens":2768890,"totalCostUsd":206.05,"costSource":"db"},{"split":"full/full-spectrum","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":53,"tasks":53,"splitTasks":55,"passes":15,"passRate":0.2727272727272727,"avgScore":0.4917476833316599,"totalDurationS":91881.80399999997,"totalInputTokens":564555200,"totalOutputTokens":3659752,"totalCostUsd":116.94,"costSource":"official"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":55,"tasks":55,"splitTasks":55,"passes":14,"passRate":0.2545454545454545,"avgScore":0.4912649141058789,"totalDurationS":113963.79800000002,"totalInputTokens":101719639,"totalOutputTokens":1155113,"totalCostUsd":196.13,"costSource":"official"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":55,"tasks":55,"splitTasks":55,"passes":14,"passRate":0.2545454545454545,"avgScore":0.4791621305194552,"totalDurationS":116604.024,"totalInputTokens":97348578,"totalOutputTokens":999008,"totalCostUsd":181.22,"costSource":"official"},{"split":"full/full-spectrum","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":55,"tasks":55,"splitTasks":55,"passes":16,"passRate":0.2909090909090909,"avgScore":0.4786170424116364,"totalDurationS":140598.485,"totalInputTokens":586176490,"totalOutputTokens":3346417,"totalCostUsd":527.28,"costSource":"official"},{"split":"full/full-spectrum","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":53,"tasks":53,"splitTasks":55,"passes":16,"passRate":0.2909090909090909,"avgScore":0.4743931539453417,"totalDurationS":65891.88000000003,"totalInputTokens":623089584,"totalOutputTokens":3760521,"totalCostUsd":129.79,"costSource":"official"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":106,"tasks":55,"splitTasks":55,"passes":33,"passRate":0.3,"avgScore":0.46575439428821086,"totalDurationS":103616.69649999999,"totalInputTokens":235438015,"totalOutputTokens":1304709,"totalCostUsd":256.09,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":53,"tasks":53,"splitTasks":55,"passes":13,"passRate":0.23636363636363636,"avgScore":0.46354442255769973,"totalDurationS":207159.591,"totalInputTokens":392062495,"totalOutputTokens":3623554,"totalCostUsd":149.3,"costSource":"db"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":107,"tasks":55,"splitTasks":55,"passes":29,"passRate":0.2727272727272727,"avgScore":0.46188106408078433,"totalDurationS":137684.5,"totalInputTokens":316865419,"totalOutputTokens":1818837,"totalCostUsd":149.75,"costSource":"list"},{"split":"full/full-spectrum","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":55,"tasks":55,"splitTasks":55,"passes":13,"passRate":0.23636363636363636,"avgScore":0.4524131245104376,"totalDurationS":152846.08700000006,"totalInputTokens":753681051,"totalOutputTokens":5129238,"totalCostUsd":685.41,"costSource":"official"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":109,"tasks":55,"splitTasks":55,"passes":27,"passRate":0.2545454545454545,"avgScore":0.4512408408905345,"totalDurationS":101382.878,"totalInputTokens":286317444,"totalOutputTokens":1756446.1666666667,"totalCostUsd":298.46,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":54,"tasks":54,"splitTasks":55,"passes":13,"passRate":0.23636363636363636,"avgScore":0.44940530822949676,"totalDurationS":233738.59900000002,"totalInputTokens":297756425,"totalOutputTokens":2433240,"totalCostUsd":143.86,"costSource":"db"},{"split":"full/full-spectrum","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":55,"tasks":55,"splitTasks":55,"passes":13,"passRate":0.23636363636363636,"avgScore":0.4456625622278024,"totalDurationS":107786.32800000001,"totalInputTokens":230067168,"totalOutputTokens":2071896,"totalCostUsd":114.29,"costSource":"db"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":109,"tasks":55,"splitTasks":55,"passes":29,"passRate":0.2727272727272727,"avgScore":0.4451610959401981,"totalDurationS":107957.442,"totalInputTokens":142119530.5,"totalOutputTokens":732332.5,"totalCostUsd":157.67,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":55,"tasks":55,"splitTasks":55,"passes":15,"passRate":0.2727272727272727,"avgScore":0.44319224828881304,"totalDurationS":106424.31600000004,"totalInputTokens":293673854,"totalOutputTokens":1245260,"totalCostUsd":266.3,"costSource":"official"},{"split":"full/full-spectrum","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":55,"tasks":55,"splitTasks":55,"passes":13,"passRate":0.23636363636363636,"avgScore":0.4429705328569882,"totalDurationS":98103.753,"totalInputTokens":429355468,"totalOutputTokens":2264355,"totalCostUsd":358.14,"costSource":"official"},{"split":"full/full-spectrum","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":54,"tasks":54,"splitTasks":55,"passes":14,"passRate":0.2545454545454545,"avgScore":0.43964528412968995,"totalDurationS":166400.929,"totalInputTokens":801223220,"totalOutputTokens":5412901,"totalCostUsd":737.17,"costSource":"official"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":55,"tasks":55,"splitTasks":55,"passes":15,"passRate":0.2727272727272727,"avgScore":0.4372134877427408,"totalDurationS":37502,"totalInputTokens":202023719,"totalOutputTokens":828678,"totalCostUsd":38.31,"costSource":"list"},{"split":"full/full-spectrum","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":55,"tasks":55,"splitTasks":55,"passes":13,"passRate":0.23636363636363636,"avgScore":0.4313229586002382,"totalDurationS":214602,"totalInputTokens":524284122,"totalOutputTokens":8213812,"totalCostUsd":1323.79,"costSource":"published"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":55,"tasks":55,"splitTasks":55,"passes":12,"passRate":0.21818181818181817,"avgScore":0.4309300641552605,"totalDurationS":88631.01999999999,"totalInputTokens":51266928,"totalOutputTokens":421145,"totalCostUsd":92.45,"costSource":"official"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":108,"tasks":55,"splitTasks":55,"passes":30,"passRate":0.2727272727272727,"avgScore":0.4301432864776319,"totalDurationS":107709.47,"totalInputTokens":153018341,"totalOutputTokens":942915.5,"totalCostUsd":164.83,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":55,"tasks":55,"splitTasks":55,"passes":11,"passRate":0.2,"avgScore":0.4269705346352009,"totalDurationS":66977.00700000001,"totalInputTokens":75687560,"totalOutputTokens":484297,"totalCostUsd":123.81,"costSource":"official"},{"split":"full/full-spectrum","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":55,"tasks":55,"splitTasks":55,"passes":12,"passRate":0.21818181818181817,"avgScore":0.4254520629651143,"totalDurationS":356231.91900000005,"totalInputTokens":1246333555,"totalOutputTokens":5369786,"totalCostUsd":null,"costSource":null},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":54,"tasks":54,"splitTasks":55,"passes":16,"passRate":0.2909090909090909,"avgScore":0.4253164625672212,"totalDurationS":71516,"totalInputTokens":652436878,"totalOutputTokens":2206867,"totalCostUsd":107.34,"costSource":"list"},{"split":"full/full-spectrum","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":55,"tasks":55,"splitTasks":55,"passes":14,"passRate":0.2545454545454545,"avgScore":0.4200321393939394,"totalDurationS":92024,"totalInputTokens":1120840818,"totalOutputTokens":3829080,"totalCostUsd":1826.4,"costSource":"official"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":55,"tasks":55,"splitTasks":55,"passes":15,"passRate":0.2727272727272727,"avgScore":0.41712583069964326,"totalDurationS":81285,"totalInputTokens":351830472,"totalOutputTokens":1354167,"totalCostUsd":61.13,"costSource":"list"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":110,"tasks":55,"splitTasks":55,"passes":27,"passRate":0.24545454545454545,"avgScore":0.4133817997254725,"totalDurationS":104391.5,"totalInputTokens":215779432,"totalOutputTokens":1228943,"totalCostUsd":107.55,"costSource":"list"},{"split":"full/full-spectrum","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":54,"tasks":54,"splitTasks":55,"passes":13,"passRate":0.23636363636363636,"avgScore":0.410514071141378,"totalDurationS":30454.794733498995,"totalInputTokens":54901456,"totalOutputTokens":734763,"totalCostUsd":69.9,"costSource":"db"},{"split":"full/full-spectrum","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":53,"tasks":53,"splitTasks":55,"passes":11,"passRate":0.2,"avgScore":0.39611287961350156,"totalDurationS":94079,"totalInputTokens":698108254,"totalOutputTokens":2255196,"totalCostUsd":568.52,"costSource":"published"},{"split":"full/full-spectrum","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":53,"tasks":53,"splitTasks":55,"passes":13,"passRate":0.23636363636363636,"avgScore":0.3933578199380144,"totalDurationS":153864,"totalInputTokens":582917784,"totalOutputTokens":3033504,"totalCostUsd":289.33,"costSource":"db"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":107,"tasks":55,"splitTasks":55,"passes":22,"passRate":0.2,"avgScore":0.39251001823093684,"totalDurationS":84078.859,"totalInputTokens":73118181.5,"totalOutputTokens":437364.5,"totalCostUsd":76.91,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":109,"tasks":55,"splitTasks":55,"passes":22,"passRate":0.20909090909090908,"avgScore":0.3891446401864527,"totalDurationS":131295.6195,"totalInputTokens":164102242.5,"totalOutputTokens":940673.5,"totalCostUsd":83.43,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":107,"tasks":55,"splitTasks":55,"passes":24,"passRate":0.21818181818181817,"avgScore":0.38707504844115914,"totalDurationS":106548.5,"totalInputTokens":142776399,"totalOutputTokens":2245802,"totalCostUsd":178.34,"costSource":"db"},{"split":"full/full-spectrum","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":55,"tasks":55,"splitTasks":55,"passes":11,"passRate":0.2,"avgScore":0.38265263820134726,"totalDurationS":158175,"totalInputTokens":300355769,"totalOutputTokens":5612384,"totalCostUsd":855.55,"costSource":"published"},{"split":"full/full-spectrum","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":53,"tasks":53,"splitTasks":55,"passes":11,"passRate":0.2,"avgScore":0.37616366308547566,"totalDurationS":53276.67023467668,"totalInputTokens":215576200,"totalOutputTokens":1889131,"totalCostUsd":841.57,"costSource":"official+adj"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":160,"tasks":55,"splitTasks":55,"passes":37,"passRate":0.22424242424242422,"avgScore":0.37550806805261017,"totalDurationS":75446.90317553736,"totalInputTokens":130833923,"totalOutputTokens":1174007,"totalCostUsd":130.35,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":54,"tasks":54,"splitTasks":55,"passes":10,"passRate":0.18181818181818182,"avgScore":0.36974012794692096,"totalDurationS":128703,"totalInputTokens":338828819,"totalOutputTokens":2676225,"totalCostUsd":389.75,"costSource":"db"},{"split":"full/full-spectrum","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":52,"tasks":52,"splitTasks":55,"passes":10,"passRate":0.18181818181818182,"avgScore":0.3661224944997091,"totalDurationS":55840.03182199924,"totalInputTokens":288810311,"totalOutputTokens":1669212,"totalCostUsd":246.46,"costSource":"official"},{"split":"full/full-spectrum","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":57,"tasks":55,"splitTasks":55,"passes":12,"passRate":0.20909090909090908,"avgScore":0.35374968752637187,"totalDurationS":115842,"totalInputTokens":327686352,"totalOutputTokens":3672954.5,"totalCostUsd":608.41,"costSource":"official"},{"split":"full/full-spectrum","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":50,"tasks":50,"splitTasks":55,"passes":10,"passRate":0.18181818181818182,"avgScore":0.3519490303044795,"totalDurationS":56202.44506297966,"totalInputTokens":58598314,"totalOutputTokens":792157,"totalCostUsd":68.85,"costSource":"list"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":110,"tasks":55,"splitTasks":55,"passes":20,"passRate":0.18181818181818182,"avgScore":0.3447683087393445,"totalDurationS":82708.247,"totalInputTokens":54493605,"totalOutputTokens":398065.5,"totalCostUsd":30.84,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":71,"tasks":54,"splitTasks":55,"passes":13,"passRate":0.19393939393939394,"avgScore":0.3434147041110992,"totalDurationS":208103.63729115008,"totalInputTokens":239603010.16666666,"totalOutputTokens":2920663.6666666665,"totalCostUsd":122.6,"costSource":"db"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":109,"tasks":55,"splitTasks":55,"passes":20,"passRate":0.18181818181818182,"avgScore":0.3399830316257406,"totalDurationS":101329.218,"totalInputTokens":78942311.5,"totalOutputTokens":555237.5,"totalCostUsd":43.6,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":52,"tasks":52,"splitTasks":55,"passes":11,"passRate":0.2,"avgScore":0.33988274762503207,"totalDurationS":62650.35733736605,"totalInputTokens":36415887,"totalOutputTokens":552100,"totalCostUsd":49.67,"costSource":"list"},{"split":"full/full-spectrum","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":50,"tasks":50,"splitTasks":55,"passes":10,"passRate":0.18181818181818182,"avgScore":0.333952530257971,"totalDurationS":82657.90435112063,"totalInputTokens":98557834,"totalOutputTokens":1053767,"totalCostUsd":101.27,"costSource":"db"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":54,"tasks":54,"splitTasks":55,"passes":9,"passRate":0.16363636363636364,"avgScore":0.33301050066448096,"totalDurationS":96800,"totalInputTokens":102418661,"totalOutputTokens":1067638,"totalCostUsd":127.95,"costSource":"db"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":55,"tasks":55,"splitTasks":55,"passes":9,"passRate":0.16363636363636364,"avgScore":0.3240193712304323,"totalDurationS":53351,"totalInputTokens":29465113,"totalOutputTokens":425304,"totalCostUsd":45.35,"costSource":"db"},{"split":"full/full-spectrum","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":52,"tasks":52,"splitTasks":55,"passes":10,"passRate":0.18181818181818182,"avgScore":0.32025184597733924,"totalDurationS":92480,"totalInputTokens":130048683,"totalOutputTokens":1072928,"totalCostUsd":67.71,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":55,"tasks":55,"splitTasks":55,"passes":7,"passRate":0.12727272727272726,"avgScore":0.3007389590993101,"totalDurationS":32130,"totalInputTokens":85588559,"totalOutputTokens":355569,"totalCostUsd":18.13,"costSource":"list"},{"split":"full/full-spectrum","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":50,"tasks":50,"splitTasks":55,"passes":7,"passRate":0.12727272727272726,"avgScore":0.29108336390143064,"totalDurationS":43471.418552602874,"totalInputTokens":201998860,"totalOutputTokens":1546037,"totalCostUsd":747.4,"costSource":"official+adj"},{"split":"full/full-spectrum","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":54,"tasks":54,"splitTasks":55,"passes":6,"passRate":0.10909090909090909,"avgScore":0.2873379749190263,"totalDurationS":171502,"totalInputTokens":118264612,"totalOutputTokens":1117633,"totalCostUsd":485.88,"costSource":"official+adj"},{"split":"full/full-spectrum","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":53,"tasks":53,"splitTasks":55,"passes":6,"passRate":0.10909090909090909,"avgScore":0.2849168408005203,"totalDurationS":128744,"totalInputTokens":585062442,"totalOutputTokens":7084714,"totalCostUsd":280.32,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":51,"tasks":51,"splitTasks":55,"passes":6,"passRate":0.10909090909090909,"avgScore":0.274703254822263,"totalDurationS":107204.82072244062,"totalInputTokens":162969004,"totalOutputTokens":1135215,"totalCostUsd":369.56,"costSource":"official+adj"},{"split":"full/full-spectrum","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":54,"tasks":54,"splitTasks":55,"passes":7,"passRate":0.12727272727272726,"avgScore":0.2638640137671591,"totalDurationS":92042,"totalInputTokens":481651301,"totalOutputTokens":1728321,"totalCostUsd":961.76,"costSource":"db+list+adj"},{"split":"full/full-spectrum","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":55,"tasks":55,"splitTasks":55,"passes":4,"passRate":0.07272727272727272,"avgScore":0.24891449790392856,"totalDurationS":19943,"totalInputTokens":36303840,"totalOutputTokens":207513,"totalCostUsd":9.01,"costSource":"list"},{"split":"full/full-spectrum","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":52,"tasks":52,"splitTasks":55,"passes":7,"passRate":0.12727272727272726,"avgScore":0.24093001414387707,"totalDurationS":168781,"totalInputTokens":644923665,"totalOutputTokens":8060919,"totalCostUsd":171.28,"costSource":"db"},{"split":"full/full-spectrum","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":97,"tasks":54,"splitTasks":55,"passes":12,"passRate":0.10909090909090909,"avgScore":0.23799048181818186,"totalDurationS":137517.33694275937,"totalInputTokens":114460972.5,"totalOutputTokens":1483905.8333333333,"totalCostUsd":68.1,"costSource":"db"},{"split":"full/full-spectrum","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":56,"tasks":52,"splitTasks":55,"passes":6,"passRate":0.10909090909090909,"avgScore":0.23585057575757576,"totalDurationS":226023.81774288748,"totalInputTokens":1636895147,"totalOutputTokens":1744287,"totalCostUsd":1391.91,"costSource":"db+adj"},{"split":"full/full-spectrum","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":54,"tasks":54,"splitTasks":55,"passes":5,"passRate":0.09090909090909091,"avgScore":0.22938917318771823,"totalDurationS":81361.152385172,"totalInputTokens":595700026,"totalOutputTokens":929990,"totalCostUsd":178.85,"costSource":"db"},{"split":"full/full-spectrum","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":97,"tasks":54,"splitTasks":55,"passes":8,"passRate":0.08181818181818182,"avgScore":0.2290770537090957,"totalDurationS":167817.14606574166,"totalInputTokens":322063737.3333333,"totalOutputTokens":3070232.3333333335,"totalCostUsd":110.66,"costSource":"db"},{"split":"full/full-spectrum","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":90,"tasks":49,"splitTasks":55,"passes":10,"passRate":0.09090909090909091,"avgScore":0.21708428055845586,"totalDurationS":222992.05093784933,"totalInputTokens":282398618,"totalOutputTokens":2238257.5,"totalCostUsd":165.44,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":98,"tasks":54,"splitTasks":55,"passes":9,"passRate":0.09090909090909091,"avgScore":0.20754532410468568,"totalDurationS":125442.30073191645,"totalInputTokens":159897475.16666666,"totalOutputTokens":1362370.8333333333,"totalCostUsd":16.57,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":52,"tasks":50,"splitTasks":55,"passes":4,"passRate":0.07272727272727272,"avgScore":0.1831974303030303,"totalDurationS":37794.73970066117,"totalInputTokens":73978311.66666667,"totalOutputTokens":896199.6666666666,"totalCostUsd":94.71,"costSource":"list"},{"split":"full/full-spectrum","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":87,"tasks":54,"splitTasks":55,"passes":6,"passRate":0.06363636363636363,"avgScore":0.1820768032937401,"totalDurationS":264884.5961624289,"totalInputTokens":93552781,"totalOutputTokens":2428431.5,"totalCostUsd":41.17,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":95,"tasks":54,"splitTasks":55,"passes":4,"passRate":0.03636363636363636,"avgScore":0.1354189575757576,"totalDurationS":89081.6723711512,"totalInputTokens":51642552.5,"totalOutputTokens":1027624.5,"totalCostUsd":25.31,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":53,"tasks":50,"splitTasks":55,"passes":3,"passRate":0.05454545454545454,"avgScore":0.12991377341047364,"totalDurationS":14418.3299197132,"totalInputTokens":21103769.5,"totalOutputTokens":179972,"totalCostUsd":66.01,"costSource":"db"},{"split":"full/full-spectrum","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":20,"tasks":20,"splitTasks":55,"passes":2,"passRate":0.03636363636363636,"avgScore":0.10856285924276156,"totalDurationS":11256.058063949225,"totalInputTokens":39918384,"totalOutputTokens":472069,"totalCostUsd":166.81,"costSource":"official+adj"},{"split":"full/full-spectrum","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":85,"tasks":54,"splitTasks":55,"passes":2,"passRate":0.03636363636363636,"avgScore":0.08422727272727273,"totalDurationS":166639.72889767349,"totalInputTokens":95157073.66666667,"totalOutputTokens":1732033.6666666667,"totalCostUsd":9.56,"costSource":"db+list"},{"split":"full/full-spectrum","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":52,"tasks":50,"splitTasks":55,"passes":2,"passRate":0.03636363636363636,"avgScore":0.07652873704683727,"totalDurationS":24283.38227561186,"totalInputTokens":61910310.5,"totalOutputTokens":1024866.5,"totalCostUsd":39.58,"costSource":"db"},{"split":"full/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":37,"tasks":37,"splitTasks":38,"passes":4,"passRate":0.10526315789473684,"avgScore":0.2735795691668936,"totalDurationS":142350.16100000002,"totalInputTokens":203627559,"totalOutputTokens":1295881,"totalCostUsd":309.97,"costSource":"official"},{"split":"full/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":37,"tasks":37,"splitTasks":38,"passes":3,"passRate":0.07894736842105263,"avgScore":0.27088054778032583,"totalDurationS":167405.486,"totalInputTokens":237812212,"totalOutputTokens":1728616,"totalCostUsd":375.11,"costSource":"official"},{"split":"full/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":37,"tasks":37,"splitTasks":38,"passes":4,"passRate":0.10526315789473684,"avgScore":0.2681142079899768,"totalDurationS":219388.75400000002,"totalInputTokens":209022458,"totalOutputTokens":2197914,"totalCostUsd":369.05,"costSource":"official"},{"split":"full/last-exam","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":36,"tasks":36,"splitTasks":38,"passes":4,"passRate":0.10526315789473684,"avgScore":0.25832168462808225,"totalDurationS":257325.22499999998,"totalInputTokens":600447110,"totalOutputTokens":1903547,"totalCostUsd":532.48,"costSource":"official"},{"split":"full/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":37,"tasks":37,"splitTasks":38,"passes":4,"passRate":0.10526315789473684,"avgScore":0.2560330126381035,"totalDurationS":148695.095,"totalInputTokens":223341619,"totalOutputTokens":1067939,"totalCostUsd":313.26,"costSource":"official"},{"split":"full/last-exam","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":35,"tasks":35,"splitTasks":38,"passes":3,"passRate":0.07894736842105263,"avgScore":0.24941857351090121,"totalDurationS":154492.59,"totalInputTokens":1027461583,"totalOutputTokens":4085104,"totalCostUsd":194.15,"costSource":"official"},{"split":"full/last-exam","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":36,"tasks":36,"splitTasks":38,"passes":4,"passRate":0.10526315789473684,"avgScore":0.241291868854736,"totalDurationS":344446.109,"totalInputTokens":559312348,"totalOutputTokens":4782419,"totalCostUsd":216.63,"costSource":"db"},{"split":"full/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":37,"tasks":37,"splitTasks":38,"passes":4,"passRate":0.10526315789473684,"avgScore":0.24006575548927744,"totalDurationS":126236.58899999999,"totalInputTokens":180346522,"totalOutputTokens":697894,"totalCostUsd":244.32,"costSource":"official"},{"split":"full/last-exam","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":35,"tasks":35,"splitTasks":38,"passes":4,"passRate":0.10526315789473684,"avgScore":0.23848830822660094,"totalDurationS":140621.53900000002,"totalInputTokens":1164697335,"totalOutputTokens":4949401,"totalCostUsd":224.75,"costSource":"official"},{"split":"full/last-exam","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":37,"tasks":37,"splitTasks":38,"passes":4,"passRate":0.10526315789473684,"avgScore":0.23700752323542038,"totalDurationS":171781.49400000004,"totalInputTokens":223738865,"totalOutputTokens":1749767,"totalCostUsd":114.79,"costSource":"db"},{"split":"full/last-exam","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":37,"tasks":37,"splitTasks":38,"passes":4,"passRate":0.10526315789473684,"avgScore":0.23424092924633108,"totalDurationS":319813.3989999999,"totalInputTokens":1263932668,"totalOutputTokens":7344733,"totalCostUsd":1160.93,"costSource":"official"},{"split":"full/last-exam","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":36,"tasks":36,"splitTasks":38,"passes":3,"passRate":0.07894736842105263,"avgScore":0.23044684825661507,"totalDurationS":225221.90099999998,"totalInputTokens":753577060,"totalOutputTokens":2762575,"totalCostUsd":637.77,"costSource":"official"},{"split":"full/last-exam","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":36,"tasks":36,"splitTasks":38,"passes":3,"passRate":0.07894736842105263,"avgScore":0.22412570860784023,"totalDurationS":252979.55200000003,"totalInputTokens":900970665,"totalOutputTokens":4277606,"totalCostUsd":830.99,"costSource":"official"},{"split":"full/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":37,"tasks":37,"splitTasks":38,"passes":3,"passRate":0.07894736842105263,"avgScore":0.21952198936326783,"totalDurationS":134630.385,"totalInputTokens":318546142,"totalOutputTokens":634334,"totalCostUsd":382.59,"costSource":"official"},{"split":"full/last-exam","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":37,"tasks":37,"splitTasks":38,"passes":4,"passRate":0.10526315789473684,"avgScore":0.2055276315873776,"totalDurationS":330764.91299999994,"totalInputTokens":748185123,"totalOutputTokens":3125141,"totalCostUsd":308.4,"costSource":"db"},{"split":"full/last-exam","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":36,"tasks":36,"splitTasks":38,"passes":3,"passRate":0.07894736842105263,"avgScore":0.2049303255658983,"totalDurationS":363134.68600000005,"totalInputTokens":437612423,"totalOutputTokens":2624214,"totalCostUsd":200.05,"costSource":"db"},{"split":"full/last-exam","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":34,"tasks":34,"splitTasks":38,"passes":5,"passRate":0.13157894736842105,"avgScore":0.19748034060237404,"totalDurationS":270327.695,"totalInputTokens":1007970909,"totalOutputTokens":5134701,"totalCostUsd":951.52,"costSource":"official"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":75,"tasks":38,"splitTasks":38,"passes":2,"passRate":0.039473684210526314,"avgScore":0.19420078029613763,"totalDurationS":117354.5,"totalInputTokens":294882387,"totalOutputTokens":783893.5,"totalCostUsd":249.88,"costSource":"list"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":77,"tasks":38,"splitTasks":38,"passes":4,"passRate":0.05263157894736842,"avgScore":0.19372652851069314,"totalDurationS":139971,"totalInputTokens":352326664.8333333,"totalOutputTokens":1396392.3333333333,"totalCostUsd":324.61,"costSource":"list"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":75,"tasks":38,"splitTasks":38,"passes":3,"passRate":0.05263157894736842,"avgScore":0.1868668857038979,"totalDurationS":140665,"totalInputTokens":297522834,"totalOutputTokens":1062195,"totalCostUsd":252.66,"costSource":"list"},{"split":"full/last-exam","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":36,"tasks":36,"splitTasks":38,"passes":3,"passRate":0.07894736842105263,"avgScore":0.16495248496656564,"totalDurationS":108947,"totalInputTokens":1585478623,"totalOutputTokens":3847061,"totalCostUsd":2091.31,"costSource":"official"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":79,"tasks":38,"splitTasks":38,"passes":2,"passRate":0.02631578947368421,"avgScore":0.1644048385293532,"totalDurationS":154166.1666666667,"totalInputTokens":523793885.5,"totalOutputTokens":2091747,"totalCostUsd":488.13,"costSource":"list"},{"split":"full/last-exam","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":74,"tasks":38,"splitTasks":38,"passes":1,"passRate":0.013157894736842105,"avgScore":0.160932671435888,"totalDurationS":153534.5,"totalInputTokens":316923871.5,"totalOutputTokens":2234417.5,"totalCostUsd":283.24,"costSource":"db"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":36,"tasks":36,"splitTasks":38,"passes":1,"passRate":0.02631578947368421,"avgScore":0.1496761918512072,"totalDurationS":113686,"totalInputTokens":1356495846,"totalOutputTokens":2624201,"totalCostUsd":197,"costSource":"list"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":74,"tasks":38,"splitTasks":38,"passes":2,"passRate":0.02631578947368421,"avgScore":0.14914850377407576,"totalDurationS":183287.5,"totalInputTokens":678056488.1666666,"totalOutputTokens":2240925.3333333335,"totalCostUsd":264.49,"costSource":"list"},{"split":"full/last-exam","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":35,"tasks":35,"splitTasks":38,"passes":1,"passRate":0.02631578947368421,"avgScore":0.14726424569791585,"totalDurationS":410964.91899999994,"totalInputTokens":894801044,"totalOutputTokens":4063160,"totalCostUsd":null,"costSource":null},{"split":"full/last-exam","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":37,"tasks":37,"splitTasks":38,"passes":1,"passRate":0.02631578947368421,"avgScore":0.1440505369585742,"totalDurationS":305062,"totalInputTokens":961017525,"totalOutputTokens":7274340,"totalCostUsd":1805.3,"costSource":"published"},{"split":"full/last-exam","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":37,"tasks":37,"splitTasks":38,"passes":1,"passRate":0.02631578947368421,"avgScore":0.14192087907608547,"totalDurationS":149774,"totalInputTokens":153886147,"totalOutputTokens":904996,"totalCostUsd":167.24,"costSource":"db"},{"split":"full/last-exam","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":103,"tasks":38,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.13388631862928818,"totalDurationS":119659.35271642619,"totalInputTokens":216406972,"totalOutputTokens":1211914,"totalCostUsd":187.64,"costSource":"db+list"},{"split":"full/last-exam","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":34,"tasks":34,"splitTasks":38,"passes":1,"passRate":0.02631578947368421,"avgScore":0.12862606139319707,"totalDurationS":172545,"totalInputTokens":782672511,"totalOutputTokens":2708597,"totalCostUsd":638.49,"costSource":"db"},{"split":"full/last-exam","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":32,"tasks":32,"splitTasks":38,"passes":1,"passRate":0.02631578947368421,"avgScore":0.12815059202118556,"totalDurationS":49458.08196799901,"totalInputTokens":126287850,"totalOutputTokens":704360,"totalCostUsd":107.32,"costSource":"db"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":74,"tasks":37,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.1261806657735013,"totalDurationS":109927.33333333333,"totalInputTokens":111296708,"totalOutputTokens":408600.3333333333,"totalCostUsd":96.13,"costSource":"list"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":72,"tasks":38,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.1256614965929625,"totalDurationS":92032.5,"totalInputTokens":90624808.5,"totalOutputTokens":486691,"totalCostUsd":43.29,"costSource":"list"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":72,"tasks":37,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.11983054733814444,"totalDurationS":102194.5,"totalInputTokens":236864478.5,"totalOutputTokens":967459,"totalCostUsd":105.65,"costSource":"list"},{"split":"full/last-exam","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":26,"tasks":26,"splitTasks":38,"passes":1,"passRate":0.02631578947368421,"avgScore":0.11436091784257574,"totalDurationS":66683.20773970685,"totalInputTokens":121011885,"totalOutputTokens":1184118,"totalCostUsd":587.73,"costSource":"official+adj"},{"split":"full/last-exam","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":31,"tasks":29,"splitTasks":38,"passes":1,"passRate":0.02631578947368421,"avgScore":0.11267746971606471,"totalDurationS":95199.99296236214,"totalInputTokens":83601379,"totalOutputTokens":551805,"totalCostUsd":75.62,"costSource":"list"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":75,"tasks":38,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.1122775555549231,"totalDurationS":86350,"totalInputTokens":65899280,"totalOutputTokens":335902,"totalCostUsd":31.18,"costSource":"list"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":38,"tasks":38,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.10993413212460641,"totalDurationS":75483,"totalInputTokens":284905745,"totalOutputTokens":772005,"totalCostUsd":46.64,"costSource":"list"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":38,"tasks":38,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.10970741091203197,"totalDurationS":108705,"totalInputTokens":742917153,"totalOutputTokens":1343720,"totalCostUsd":109.66,"costSource":"list"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":73,"tasks":38,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.1092923011990062,"totalDurationS":120135.5,"totalInputTokens":449191663,"totalOutputTokens":1428521,"totalCostUsd":185.5,"costSource":"list"},{"split":"full/last-exam","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":29,"tasks":29,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.10874277625057213,"totalDurationS":89528.58231328387,"totalInputTokens":178227464,"totalOutputTokens":996954,"totalCostUsd":154.51,"costSource":"db"},{"split":"full/last-exam","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":29,"tasks":29,"splitTasks":38,"passes":1,"passRate":0.02631578947368421,"avgScore":0.10732247368421054,"totalDurationS":61917.92565060669,"totalInputTokens":63892750,"totalOutputTokens":456416,"totalCostUsd":61.49,"costSource":"list"},{"split":"full/last-exam","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":38,"tasks":38,"splitTasks":38,"passes":1,"passRate":0.02631578947368421,"avgScore":0.10431719138556748,"totalDurationS":253733,"totalInputTokens":739811872,"totalOutputTokens":5918841,"totalCostUsd":1395.12,"costSource":"published"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":38,"tasks":38,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.10395747737317527,"totalDurationS":56504,"totalInputTokens":132807946,"totalOutputTokens":319379,"totalCostUsd":23.91,"costSource":"list"},{"split":"full/last-exam","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":31,"tasks":31,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.10029435149513931,"totalDurationS":61575.264092724305,"totalInputTokens":170082318,"totalOutputTokens":1387243,"totalCostUsd":684.93,"costSource":"official+adj"},{"split":"full/last-exam","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":32,"tasks":31,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.0993785955488623,"totalDurationS":187354,"totalInputTokens":657707055.5,"totalOutputTokens":2444295.5,"totalCostUsd":318.57,"costSource":"db"},{"split":"full/last-exam","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":38,"tasks":38,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.09880317382248731,"totalDurationS":57793,"totalInputTokens":59361487,"totalOutputTokens":378037,"totalCostUsd":64.34,"costSource":"db"},{"split":"full/last-exam","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":32,"tasks":32,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.09061195643997812,"totalDurationS":271816,"totalInputTokens":455947732,"totalOutputTokens":4779382,"totalCostUsd":84.7,"costSource":"db"},{"split":"full/last-exam","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":38,"tasks":38,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.08890663199918114,"totalDurationS":22384,"totalInputTokens":42591540,"totalOutputTokens":162532,"totalCostUsd":8.62,"costSource":"list"},{"split":"full/last-exam","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":28,"tasks":28,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.08756310526315789,"totalDurationS":125016,"totalInputTokens":150993237,"totalOutputTokens":948341,"totalCostUsd":77.87,"costSource":"db+list"},{"split":"full/last-exam","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":31,"tasks":31,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.08134244963505957,"totalDurationS":63550.53847987812,"totalInputTokens":321376028,"totalOutputTokens":540717,"totalCostUsd":100.25,"costSource":"db"},{"split":"full/last-exam","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":20,"tasks":20,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.08029413579144805,"totalDurationS":37053.47873265087,"totalInputTokens":145716643,"totalOutputTokens":920145,"totalCostUsd":495.79,"costSource":"official+adj"},{"split":"full/last-exam","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":31,"tasks":31,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.07863300882269293,"totalDurationS":155269.84613300068,"totalInputTokens":707313906,"totalOutputTokens":2192916,"totalCostUsd":593.61,"costSource":"official"},{"split":"full/last-exam","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":37,"tasks":31,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.07318078210639797,"totalDurationS":130535.2900615723,"totalInputTokens":206932842.16666666,"totalOutputTokens":2518416,"totalCostUsd":106.76,"costSource":"db"},{"split":"full/last-exam","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":32,"tasks":32,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.069505480733747,"totalDurationS":155287,"totalInputTokens":841102097,"totalOutputTokens":2207676,"totalCostUsd":734.85,"costSource":"published"},{"split":"full/last-exam","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":33,"tasks":33,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.06390764530880215,"totalDurationS":118997,"totalInputTokens":377757993,"totalOutputTokens":4129312,"totalCostUsd":173.41,"costSource":"db+list"},{"split":"full/last-exam","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":54,"tasks":32,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.061845741706597165,"totalDurationS":205776.51792727213,"totalInputTokens":353977626.5,"totalOutputTokens":2529310.5,"totalCostUsd":203.68,"costSource":"db+list"},{"split":"full/last-exam","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":31,"tasks":30,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.052478947368421056,"totalDurationS":188112.5,"totalInputTokens":231247542.5,"totalOutputTokens":3319023.5,"totalCostUsd":838.46,"costSource":"official"},{"split":"full/last-exam","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":27,"tasks":27,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.052413157894736835,"totalDurationS":186747,"totalInputTokens":157559357,"totalOutputTokens":870700,"totalCostUsd":601.73,"costSource":"official+adj"},{"split":"full/last-exam","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":59,"tasks":33,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.049588507561410436,"totalDurationS":128733.20068769388,"totalInputTokens":228904638.83333334,"totalOutputTokens":1944406.8333333333,"totalCostUsd":78.19,"costSource":"db"},{"split":"full/last-exam","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":32,"tasks":32,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.043412991868513016,"totalDurationS":180025.200925768,"totalInputTokens":452898006,"totalOutputTokens":1462721,"totalCostUsd":841.65,"costSource":"official+adj"},{"split":"full/last-exam","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":55,"tasks":33,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.03408,"totalDurationS":118979.19944043171,"totalInputTokens":135802977,"totalOutputTokens":1277989.5,"totalCostUsd":14.92,"costSource":"db+list"},{"split":"full/last-exam","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":34,"tasks":32,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.03053947368421053,"totalDurationS":162523.19375644717,"totalInputTokens":1379338229.5,"totalOutputTokens":1139995.5,"totalCostUsd":1200.21,"costSource":"db+adj"},{"split":"full/last-exam","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":59,"tasks":33,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.02521315789473684,"totalDurationS":140834.02247361047,"totalInputTokens":208751569.5,"totalOutputTokens":1659819.1666666667,"totalCostUsd":108.13,"costSource":"db"},{"split":"full/last-exam","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":35,"tasks":33,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.023470736842105263,"totalDurationS":41727.032814611164,"totalInputTokens":56200501.5,"totalOutputTokens":477321.5,"totalCostUsd":71.44,"costSource":"list"},{"split":"full/last-exam","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":57,"tasks":33,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.02322167105263158,"totalDurationS":90257.39144980125,"totalInputTokens":47245869.5,"totalOutputTokens":621333,"totalCostUsd":22.18,"costSource":"db+list"},{"split":"full/last-exam","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":33,"tasks":32,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.018223973684210526,"totalDurationS":26049.82843146904,"totalInputTokens":11494377,"totalOutputTokens":127211,"totalCostUsd":36.39,"costSource":"db"},{"split":"full/last-exam","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":48,"tasks":33,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.01640722406550101,"totalDurationS":218740.34341101287,"totalInputTokens":88077257,"totalOutputTokens":1829053.5,"totalCostUsd":38.87,"costSource":"db+list"},{"split":"full/last-exam","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":47,"tasks":33,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.012792105263157895,"totalDurationS":159244.5490859223,"totalInputTokens":87693128.5,"totalOutputTokens":1462761.8333333333,"totalCostUsd":9.15,"costSource":"db+list"},{"split":"full/last-exam","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":30,"tasks":30,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0.009123684210526317,"totalDurationS":144134,"totalInputTokens":497315638,"totalOutputTokens":821016,"totalCostUsd":732.51,"costSource":"db+list+adj"},{"split":"full/last-exam","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":34,"tasks":33,"splitTasks":38,"passes":0,"passRate":0,"avgScore":0,"totalDurationS":43037.737046774244,"totalInputTokens":66463287.5,"totalOutputTokens":1142116.5,"totalCostUsd":45.9,"costSource":"db"},{"split":"full/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":35,"passRate":0.5223880597014925,"avgScore":0.8226486188473473,"totalDurationS":93047.98500000002,"totalInputTokens":150615812,"totalOutputTokens":1446631,"totalCostUsd":272.06,"costSource":"official"},{"split":"full/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":67,"tasks":67,"splitTasks":67,"passes":32,"passRate":0.47761194029850745,"avgScore":0.8117506107197706,"totalDurationS":44003.758999999984,"totalInputTokens":139204598,"totalOutputTokens":594788,"totalCostUsd":202.7,"costSource":"official"},{"split":"full/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":67,"tasks":67,"splitTasks":67,"passes":34,"passRate":0.5074626865671642,"avgScore":0.8115622985142538,"totalDurationS":182552.064,"totalInputTokens":194978075,"totalOutputTokens":2085365,"totalCostUsd":359.87,"costSource":"official"},{"split":"full/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":67,"tasks":67,"splitTasks":67,"passes":33,"passRate":0.4925373134328358,"avgScore":0.8070988728515733,"totalDurationS":94306.28199999998,"totalInputTokens":129474576,"totalOutputTokens":1202826,"totalCostUsd":234.48,"costSource":"official"},{"split":"full/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":67,"tasks":67,"splitTasks":67,"passes":32,"passRate":0.47761194029850745,"avgScore":0.7964692243666142,"totalDurationS":57713.38899999999,"totalInputTokens":113981530,"totalOutputTokens":781431,"totalCostUsd":188.45,"costSource":"official"},{"split":"full/near-term","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":31,"passRate":0.4626865671641791,"avgScore":0.795384403782699,"totalDurationS":152327.13999999998,"totalInputTokens":702254162,"totalOutputTokens":4651765,"totalCostUsd":647.3,"costSource":"official"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":134,"tasks":67,"splitTasks":67,"passes":63,"passRate":0.47761194029850745,"avgScore":0.7882473228071811,"totalDurationS":145737.33333333334,"totalInputTokens":304163441.3333333,"totalOutputTokens":1816516,"totalCostUsd":322.09,"costSource":"list"},{"split":"full/near-term","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":66,"tasks":66,"splitTasks":67,"passes":32,"passRate":0.47761194029850745,"avgScore":0.7864883060651019,"totalDurationS":109483.99199999997,"totalInputTokens":470809193,"totalOutputTokens":3162955,"totalCostUsd":429.73,"costSource":"official"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":134,"tasks":67,"splitTasks":67,"passes":61,"passRate":0.4552238805970149,"avgScore":0.7829241382323966,"totalDurationS":125006.5,"totalInputTokens":189978516.33333334,"totalOutputTokens":1282200,"totalCostUsd":210.38,"costSource":"list"},{"split":"full/near-term","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":67,"tasks":67,"splitTasks":67,"passes":29,"passRate":0.43283582089552236,"avgScore":0.7791930500930184,"totalDurationS":60207.228,"totalInputTokens":436608868,"totalOutputTokens":4037190,"totalCostUsd":102.98,"costSource":"official"},{"split":"full/near-term","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":32,"passRate":0.47761194029850745,"avgScore":0.7781381327058974,"totalDurationS":66026.07000000002,"totalInputTokens":457986200,"totalOutputTokens":3799113,"totalCostUsd":102.58,"costSource":"official"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":132,"tasks":67,"splitTasks":67,"passes":62,"passRate":0.4701492537313433,"avgScore":0.775482331051408,"totalDurationS":120620.5,"totalInputTokens":155266763,"totalOutputTokens":1008998,"totalCostUsd":172.04,"costSource":"list"},{"split":"full/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":67,"tasks":67,"splitTasks":67,"passes":32,"passRate":0.47761194029850745,"avgScore":0.7662415009285244,"totalDurationS":44720.217000000004,"totalInputTokens":84728024,"totalOutputTokens":531724,"totalCostUsd":139.47,"costSource":"official"},{"split":"full/near-term","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":67,"tasks":67,"splitTasks":67,"passes":30,"passRate":0.44776119402985076,"avgScore":0.7650876361906394,"totalDurationS":159027.705,"totalInputTokens":761793318,"totalOutputTokens":5478458,"totalCostUsd":737.47,"costSource":"official"},{"split":"full/near-term","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":67,"tasks":67,"splitTasks":67,"passes":30,"passRate":0.44776119402985076,"avgScore":0.7589191181617984,"totalDurationS":115842.56199999998,"totalInputTokens":326611054,"totalOutputTokens":2003422,"totalCostUsd":328.27,"costSource":"official"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":33,"passRate":0.4925373134328358,"avgScore":0.7562644213793285,"totalDurationS":69711,"totalInputTokens":359705378,"totalOutputTokens":1633460,"totalCostUsd":68.71,"costSource":"list"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":134,"tasks":67,"splitTasks":67,"passes":60,"passRate":0.45273631840796025,"avgScore":0.7561914737576828,"totalDurationS":123361.5,"totalInputTokens":124228619.66666667,"totalOutputTokens":787503.5,"totalCostUsd":136.75,"costSource":"list"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":67,"tasks":67,"splitTasks":67,"passes":29,"passRate":0.43283582089552236,"avgScore":0.743547028673177,"totalDurationS":78518,"totalInputTokens":541671893,"totalOutputTokens":2191134,"totalCostUsd":95.67,"costSource":"list"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":132,"tasks":67,"splitTasks":67,"passes":58,"passRate":0.44776119402985076,"avgScore":0.7387174887795719,"totalDurationS":113197,"totalInputTokens":170739006.5,"totalOutputTokens":1313492.5,"totalCostUsd":95.88,"costSource":"list"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":132,"tasks":67,"splitTasks":67,"passes":54,"passRate":0.417910447761194,"avgScore":0.7327376744045965,"totalDurationS":133954.5,"totalInputTokens":268565325.5,"totalOutputTokens":1956342.5,"totalCostUsd":141.11,"costSource":"list"},{"split":"full/near-term","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":132,"tasks":67,"splitTasks":67,"passes":58,"passRate":0.44029850746268656,"avgScore":0.724007875487875,"totalDurationS":106336,"totalInputTokens":126210106.5,"totalOutputTokens":2256939,"totalCostUsd":170.09,"costSource":"db"},{"split":"full/near-term","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":26,"passRate":0.3880597014925373,"avgScore":0.721190499337615,"totalDurationS":224956.202,"totalInputTokens":321979548,"totalOutputTokens":4654794,"totalCostUsd":137.01,"costSource":"db"},{"split":"full/near-term","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":67,"tasks":67,"splitTasks":67,"passes":26,"passRate":0.3880597014925373,"avgScore":0.7186616124141026,"totalDurationS":75263.93899999998,"totalInputTokens":239613150,"totalOutputTokens":2034986,"totalCostUsd":121.45,"costSource":"db"},{"split":"full/near-term","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":67,"tasks":67,"splitTasks":67,"passes":27,"passRate":0.40298507462686567,"avgScore":0.7159801555439591,"totalDurationS":239761.4640000001,"totalInputTokens":270158643,"totalOutputTokens":2722015,"totalCostUsd":145.05,"costSource":"db"},{"split":"full/near-term","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":25,"passRate":0.373134328358209,"avgScore":0.7112863360362098,"totalDurationS":76455,"totalInputTokens":504938120,"totalOutputTokens":3626698,"totalCostUsd":1018.09,"costSource":"official"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":133,"tasks":67,"splitTasks":67,"passes":57,"passRate":0.43283582089552236,"avgScore":0.7084704112498615,"totalDurationS":144963,"totalInputTokens":155958887.5,"totalOutputTokens":1013526,"totalCostUsd":83.8,"costSource":"list"},{"split":"full/near-term","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":67,"tasks":67,"splitTasks":67,"passes":25,"passRate":0.373134328358209,"avgScore":0.7078849088375331,"totalDurationS":112965.67199999999,"totalInputTokens":239815799,"totalOutputTokens":1300434,"totalCostUsd":226.65,"costSource":"official"},{"split":"full/near-term","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":66,"tasks":66,"splitTasks":67,"passes":26,"passRate":0.3880597014925373,"avgScore":0.6968586979044264,"totalDurationS":182895.38799999998,"totalInputTokens":256675448,"totalOutputTokens":2162427,"totalCostUsd":129.35,"costSource":"db"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":67,"tasks":67,"splitTasks":67,"passes":24,"passRate":0.3582089552238806,"avgScore":0.6736742823508564,"totalDurationS":60584,"totalInputTokens":228811254,"totalOutputTokens":1065059,"totalCostUsd":46.18,"costSource":"list"},{"split":"full/near-term","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":67,"tasks":67,"splitTasks":67,"passes":22,"passRate":0.3283582089552239,"avgScore":0.6736635047623744,"totalDurationS":53801.491831077,"totalInputTokens":167219189,"totalOutputTokens":1025815,"totalCostUsd":147.52,"costSource":"db"},{"split":"full/near-term","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":65,"tasks":65,"splitTasks":67,"passes":25,"passRate":0.373134328358209,"avgScore":0.6719239733700241,"totalDurationS":148769.07770477302,"totalInputTokens":223015549,"totalOutputTokens":1462808,"totalCostUsd":218.12,"costSource":"db"},{"split":"full/near-term","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":198,"tasks":67,"splitTasks":67,"passes":77,"passRate":0.3905472636815919,"avgScore":0.670526220421849,"totalDurationS":97188.19844049853,"totalInputTokens":162729818,"totalOutputTokens":1307423.8333333333,"totalCostUsd":120.93,"costSource":"db+list"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":134,"tasks":67,"splitTasks":67,"passes":53,"passRate":0.3930348258706468,"avgScore":0.6677679137696316,"totalDurationS":96179.83333333334,"totalInputTokens":71044249.66666667,"totalOutputTokens":467625,"totalCostUsd":80.16,"costSource":"list"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":131,"tasks":67,"splitTasks":67,"passes":52,"passRate":0.3880597014925373,"avgScore":0.6595062733569761,"totalDurationS":130482.5,"totalInputTokens":84622600.5,"totalOutputTokens":590880,"totalCostUsd":47.32,"costSource":"list"},{"split":"full/near-term","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":72,"tasks":67,"splitTasks":67,"passes":24,"passRate":0.35074626865671643,"avgScore":0.6414472929875101,"totalDurationS":114531,"totalInputTokens":341718065,"totalOutputTokens":3125447.5,"totalCostUsd":947.17,"costSource":"official"},{"split":"full/near-term","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":66,"tasks":66,"splitTasks":67,"passes":29,"passRate":0.43283582089552236,"avgScore":0.6396884267777608,"totalDurationS":178788,"totalInputTokens":310513347,"totalOutputTokens":8274090,"totalCostUsd":1105.97,"costSource":"published"},{"split":"full/near-term","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":66,"tasks":66,"splitTasks":67,"passes":24,"passRate":0.3582089552238806,"avgScore":0.6273164650789494,"totalDurationS":151680,"totalInputTokens":201294188,"totalOutputTokens":5981020,"totalCostUsd":683.28,"costSource":"published"},{"split":"full/near-term","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":66,"tasks":66,"splitTasks":67,"passes":21,"passRate":0.31343283582089554,"avgScore":0.6269364006481253,"totalDurationS":120381.51676356932,"totalInputTokens":110261629,"totalOutputTokens":1648119,"totalCostUsd":557.68,"costSource":"official+adj"},{"split":"full/near-term","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":66,"tasks":66,"splitTasks":67,"passes":23,"passRate":0.34328358208955223,"avgScore":0.6229800382758721,"totalDurationS":79275,"totalInputTokens":94097065,"totalOutputTokens":1059727,"totalCostUsd":49.7,"costSource":"db+list"},{"split":"full/near-term","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":69,"tasks":66,"splitTasks":67,"passes":23,"passRate":0.3358208955223881,"avgScore":0.6228643923694662,"totalDurationS":108587.11174137115,"totalInputTokens":51827010,"totalOutputTokens":741097,"totalCostUsd":68.46,"costSource":"list"},{"split":"full/near-term","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":67,"tasks":67,"splitTasks":67,"passes":19,"passRate":0.2835820895522388,"avgScore":0.6172996937063634,"totalDurationS":156896,"totalInputTokens":190131175,"totalOutputTokens":1966191,"totalCostUsd":805.69,"costSource":"official+adj"},{"split":"full/near-term","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":69,"tasks":63,"splitTasks":67,"passes":21,"passRate":0.291044776119403,"avgScore":0.6171275522572685,"totalDurationS":57944.460609696805,"totalInputTokens":176244296.5,"totalOutputTokens":1470123,"totalCostUsd":737.55,"costSource":"official+adj"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":67,"tasks":67,"splitTasks":67,"passes":20,"passRate":0.29850746268656714,"avgScore":0.6092947556539312,"totalDurationS":67571,"totalInputTokens":90618587,"totalOutputTokens":452393,"totalCostUsd":19.45,"costSource":"list"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":131,"tasks":67,"splitTasks":67,"passes":41,"passRate":0.3208955223880597,"avgScore":0.6068743663111191,"totalDurationS":116658,"totalInputTokens":62201618.5,"totalOutputTokens":448088.5,"totalCostUsd":33.74,"costSource":"list"},{"split":"full/near-term","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":67,"tasks":67,"splitTasks":67,"passes":19,"passRate":0.2835820895522388,"avgScore":0.6045069241062173,"totalDurationS":74416.76165142255,"totalInputTokens":359152755,"totalOutputTokens":1944556,"totalCostUsd":311.72,"costSource":"official"},{"split":"full/near-term","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":66,"tasks":66,"splitTasks":67,"passes":22,"passRate":0.3283582089552239,"avgScore":0.6033126287817978,"totalDurationS":117886,"totalInputTokens":187022399,"totalOutputTokens":2708776,"totalCostUsd":204.15,"costSource":"db"},{"split":"full/near-term","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":68,"tasks":66,"splitTasks":67,"passes":19,"passRate":0.26865671641791045,"avgScore":0.6008599977646784,"totalDurationS":239417.5,"totalInputTokens":732654647,"totalOutputTokens":3149946.5,"totalCostUsd":375.61,"costSource":"db"},{"split":"full/near-term","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":66,"tasks":66,"splitTasks":67,"passes":21,"passRate":0.31343283582089554,"avgScore":0.6002555857554045,"totalDurationS":298438.2150000001,"totalInputTokens":684638103,"totalOutputTokens":6102227,"totalCostUsd":null,"costSource":null},{"split":"full/near-term","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":65,"tasks":65,"splitTasks":67,"passes":25,"passRate":0.373134328358209,"avgScore":0.598098576643749,"totalDurationS":76504,"totalInputTokens":397673605,"totalOutputTokens":2241277,"totalCostUsd":446,"costSource":"published"},{"split":"full/near-term","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":66,"tasks":66,"splitTasks":67,"passes":20,"passRate":0.29850746268656714,"avgScore":0.5926809886791707,"totalDurationS":48118,"totalInputTokens":81684093,"totalOutputTokens":1064184,"totalCostUsd":110.43,"costSource":"db"},{"split":"full/near-term","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":65,"tasks":65,"splitTasks":67,"passes":20,"passRate":0.29850746268656714,"avgScore":0.581507678464108,"totalDurationS":84340.52837546298,"totalInputTokens":98383491,"totalOutputTokens":962554,"totalCostUsd":105.98,"costSource":"list"},{"split":"full/near-term","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":66,"tasks":65,"splitTasks":67,"passes":19,"passRate":0.2835820895522388,"avgScore":0.5799257416141242,"totalDurationS":171722.06837378268,"totalInputTokens":201660470,"totalOutputTokens":1516121.5,"totalCostUsd":508.37,"costSource":"official+adj"},{"split":"full/near-term","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":84,"tasks":65,"splitTasks":67,"passes":30,"passRate":0.3358208955223881,"avgScore":0.578007915138166,"totalDurationS":147335.50355529715,"totalInputTokens":86038352.5,"totalOutputTokens":2379425,"totalCostUsd":68.88,"costSource":"db"},{"split":"full/near-term","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":63,"tasks":63,"splitTasks":67,"passes":15,"passRate":0.22388059701492538,"avgScore":0.5578444176897955,"totalDurationS":58636.88796496298,"totalInputTokens":120384368,"totalOutputTokens":1068334,"totalCostUsd":496.33,"costSource":"official+adj"},{"split":"full/near-term","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":65,"tasks":65,"splitTasks":67,"passes":19,"passRate":0.2835820895522388,"avgScore":0.5494600574739001,"totalDurationS":99601,"totalInputTokens":239360406,"totalOutputTokens":1099196,"totalCostUsd":341.66,"costSource":"db+list+adj"},{"split":"full/near-term","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":67,"tasks":67,"splitTasks":67,"passes":17,"passRate":0.2537313432835821,"avgScore":0.5353736949071799,"totalDurationS":36974,"totalInputTokens":28164467,"totalOutputTokens":528351,"totalCostUsd":48.16,"costSource":"db"},{"split":"full/near-term","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":67,"tasks":65,"splitTasks":67,"passes":18,"passRate":0.26119402985074625,"avgScore":0.4954053099301343,"totalDurationS":175033.16224954824,"totalInputTokens":616736935.5,"totalOutputTokens":938928.5,"totalCostUsd":574.73,"costSource":"db+adj"},{"split":"full/near-term","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":67,"tasks":67,"splitTasks":67,"passes":15,"passRate":0.22388059701492538,"avgScore":0.48273103955698327,"totalDurationS":50813,"totalInputTokens":46726983,"totalOutputTokens":263717,"totalCostUsd":10.56,"costSource":"list"},{"split":"full/near-term","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":67,"tasks":67,"splitTasks":67,"passes":12,"passRate":0.1791044776119403,"avgScore":0.4766278310546233,"totalDurationS":274026,"totalInputTokens":640770834,"totalOutputTokens":8883124,"totalCostUsd":200.78,"costSource":"db"},{"split":"full/near-term","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":63,"tasks":63,"splitTasks":67,"passes":12,"passRate":0.1791044776119403,"avgScore":0.46895390009159155,"totalDurationS":137430,"totalInputTokens":501983933,"totalOutputTokens":7323900,"totalCostUsd":246.83,"costSource":"db+list"},{"split":"full/near-term","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":130,"tasks":67,"splitTasks":67,"passes":27,"passRate":0.20149253731343283,"avgScore":0.45560963735192905,"totalDurationS":224248.87307640666,"totalInputTokens":183496122.83333334,"totalOutputTokens":1648850.5,"totalCostUsd":107.85,"costSource":"db"},{"split":"full/near-term","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":66,"tasks":66,"splitTasks":67,"passes":14,"passRate":0.208955223880597,"avgScore":0.45373662346275323,"totalDurationS":62517.515991543354,"totalInputTokens":178595579,"totalOutputTokens":684821,"totalCostUsd":66.17,"costSource":"db"},{"split":"full/near-term","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":133,"tasks":67,"splitTasks":67,"passes":28,"passRate":0.19900497512437812,"avgScore":0.4381171518153468,"totalDurationS":211812.18801494362,"totalInputTokens":208154198.33333334,"totalOutputTokens":1909336.6666666667,"totalCostUsd":109.06,"costSource":"db"},{"split":"full/near-term","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":131,"tasks":67,"splitTasks":67,"passes":17,"passRate":0.12686567164179105,"avgScore":0.36422336106940467,"totalDurationS":216764.1855777436,"totalInputTokens":259732239.16666666,"totalOutputTokens":2654193.3333333335,"totalCostUsd":89.59,"costSource":"db"},{"split":"full/near-term","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":119,"tasks":65,"splitTasks":67,"passes":19,"passRate":0.15671641791044777,"avgScore":0.3512706887636276,"totalDurationS":219933.07505434786,"totalInputTokens":118462415.5,"totalOutputTokens":2057036.5,"totalCostUsd":46.55,"costSource":"db+list"},{"split":"full/near-term","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":123,"tasks":67,"splitTasks":67,"passes":16,"passRate":0.11940298507462686,"avgScore":0.3508749428062655,"totalDurationS":157005.70431608308,"totalInputTokens":105443753,"totalOutputTokens":1528714,"totalCostUsd":12.77,"costSource":"db"},{"split":"full/near-term","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":70,"tasks":67,"splitTasks":67,"passes":7,"passRate":0.1044776119402985,"avgScore":0.3184800561555183,"totalDurationS":79155.77292464607,"totalInputTokens":99801742.5,"totalOutputTokens":1025449.5,"totalCostUsd":127.32,"costSource":"list"},{"split":"full/near-term","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":105,"tasks":67,"splitTasks":67,"passes":12,"passRate":0.1044776119402985,"avgScore":0.24547984743567736,"totalDurationS":228093.81403760775,"totalInputTokens":98237249.5,"totalOutputTokens":1413585,"totalCostUsd":8.86,"costSource":"db+list"},{"split":"full/near-term","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":123,"tasks":66,"splitTasks":67,"passes":9,"passRate":0.06716417910447761,"avgScore":0.24445086433509086,"totalDurationS":112501.3786811509,"totalInputTokens":73847551.5,"totalOutputTokens":1205923,"totalCostUsd":35.01,"costSource":"db+list"},{"split":"full/near-term","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":68,"tasks":67,"splitTasks":67,"passes":9,"passRate":0.13432835820895522,"avgScore":0.23974389265492613,"totalDurationS":84571.9589642135,"totalInputTokens":85510462,"totalOutputTokens":1248047,"totalCostUsd":56.14,"costSource":"db"},{"split":"full/near-term","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":67,"tasks":66,"splitTasks":67,"passes":4,"passRate":0.05970149253731343,"avgScore":0.17789172173062615,"totalDurationS":26068.0115799919,"totalInputTokens":26353968.5,"totalOutputTokens":242635,"totalCostUsd":82.7,"costSource":"db"},{"split":"full/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":151,"tasks":151,"splitTasks":152,"passes":52,"passRate":0.34210526315789475,"avgScore":0.5925587020443251,"totalDurationS":526557.0650000001,"totalInputTokens":510255691,"totalOutputTokens":5770631,"totalCostUsd":947.52,"costSource":"official"},{"split":"full/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":151,"tasks":151,"splitTasks":152,"passes":49,"passRate":0.3223684210526316,"avgScore":0.5829341986297972,"totalDurationS":346975.83300000016,"totalInputTokens":478752169,"totalOutputTokens":4189738,"totalCostUsd":820.35,"costSource":"official"},{"split":"full/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":151,"tasks":151,"splitTasks":152,"passes":48,"passRate":0.3157894736842105,"avgScore":0.5777997716313646,"totalDurationS":325797.8419999999,"totalInputTokens":420284625,"totalOutputTokens":3374771,"totalCostUsd":705.22,"costSource":"official"},{"split":"full/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":151,"tasks":151,"splitTasks":152,"passes":49,"passRate":0.3223684210526316,"avgScore":0.5762070581232449,"totalDurationS":261692.78100000005,"totalInputTokens":407254514,"totalOutputTokens":2433429,"totalCostUsd":623.9,"costSource":"official"},{"split":"full/overall","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":148,"tasks":148,"splitTasks":152,"passes":49,"passRate":0.3223684210526316,"avgScore":0.5575758972199165,"totalDurationS":290234.9759999998,"totalInputTokens":2130923906,"totalOutputTokens":11823598,"totalCostUsd":428.09,"costSource":"official"},{"split":"full/overall","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":151,"tasks":151,"splitTasks":152,"passes":46,"passRate":0.3026315789473684,"avgScore":0.5552936329794441,"totalDurationS":573533.894,"totalInputTokens":2477096511,"totalOutputTokens":15655260,"totalCostUsd":2278.49,"costSource":"official"},{"split":"full/overall","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":148,"tasks":148,"splitTasks":152,"passes":45,"passRate":0.29605263157894735,"avgScore":0.5527655474845958,"totalDurationS":271985.12600000005,"totalInputTokens":2031030687,"totalOutputTokens":11283650,"totalCostUsd":408.58,"costSource":"official"},{"split":"full/overall","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":149,"tasks":149,"splitTasks":152,"passes":48,"passRate":0.3157894736842105,"avgScore":0.5520199630375696,"totalDurationS":462563.7839999999,"totalInputTokens":1792169341,"totalOutputTokens":10118922,"totalCostUsd":1637.91,"costSource":"official"},{"split":"full/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":151,"tasks":151,"splitTasks":152,"passes":43,"passRate":0.28289473684210525,"avgScore":0.5437948986344553,"totalDurationS":223867.21800000002,"totalInputTokens":527143796,"totalOutputTokens":1656404,"totalCostUsd":696.97,"costSource":"official"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":301,"tasks":152,"splitTasks":152,"passes":93,"passRate":0.3059210526315789,"avgScore":0.5361628463309976,"totalDurationS":340729.69649999996,"totalInputTokens":762936773.1666666,"totalOutputTokens":3798417.8333333335,"totalCostUsd":771.62,"costSource":"db+list"},{"split":"full/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":151,"tasks":151,"splitTasks":152,"passes":45,"passRate":0.29605263157894735,"avgScore":0.5339594263114672,"totalDurationS":236298.854,"totalInputTokens":312003435,"totalOutputTokens":1602933,"totalCostUsd":467.03,"costSource":"official"},{"split":"full/overall","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":150,"tasks":150,"splitTasks":152,"passes":44,"passRate":0.2894736842105263,"avgScore":0.5302736569925712,"totalDurationS":402228.2569999999,"totalInputTokens":1344833416,"totalOutputTokens":6334961,"totalCostUsd":1193.47,"costSource":"official"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":307,"tasks":152,"splitTasks":152,"passes":89,"passRate":0.29605263157894735,"avgScore":0.5276278004520454,"totalDurationS":373587.878,"totalInputTokens":1095236840.8333333,"totalOutputTokens":5443524.666666667,"totalCostUsd":1084.09,"costSource":"db+list"},{"split":"full/overall","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":148,"tasks":148,"splitTasks":152,"passes":47,"passRate":0.3092105263157895,"avgScore":0.5267408894394475,"totalDurationS":560523.619,"totalInputTokens":2444275652,"totalOutputTokens":14923513,"totalCostUsd":2302.08,"costSource":"official"},{"split":"full/overall","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":148,"tasks":148,"splitTasks":152,"passes":41,"passRate":0.26973684210526316,"avgScore":0.5248561340297907,"totalDurationS":729633.2999999999,"totalInputTokens":1234201310,"totalOutputTokens":12430863,"totalCostUsd":486.47,"costSource":"db"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":299,"tasks":152,"splitTasks":152,"passes":91,"passRate":0.3059210526315789,"avgScore":0.523728673169988,"totalDurationS":340491.97,"totalInputTokens":594028867,"totalOutputTokens":2890301.5,"totalCostUsd":575.68,"costSource":"db+list"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":302,"tasks":152,"splitTasks":152,"passes":87,"passRate":0.29495614035087714,"avgScore":0.5210026942935828,"totalDurationS":328693.94200000004,"totalInputTokens":539877934.6666666,"totalOutputTokens":2196349.5,"totalCostUsd":518.72,"costSource":"db+list"},{"split":"full/overall","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":150,"tasks":150,"splitTasks":152,"passes":42,"passRate":0.27631578947368424,"avgScore":0.5190143852885959,"totalDurationS":435722.7299999999,"totalInputTokens":1003034490,"totalOutputTokens":4151470,"totalCostUsd":917.87,"costSource":"official"},{"split":"full/overall","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":149,"tasks":149,"splitTasks":152,"passes":43,"passRate":0.28289473684210525,"avgScore":0.515832318778052,"totalDurationS":669880.985,"totalInputTokens":1402173402,"totalOutputTokens":7479641,"totalCostUsd":605.78,"costSource":"db"},{"split":"full/overall","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":151,"tasks":151,"splitTasks":152,"passes":41,"passRate":0.26973684210526316,"avgScore":0.5122184380800093,"totalDurationS":320860.16600000014,"totalInputTokens":668267258,"totalOutputTokens":5447367,"totalCostUsd":336.79,"costSource":"db"},{"split":"full/overall","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":149,"tasks":149,"splitTasks":152,"passes":41,"passRate":0.26973684210526316,"avgScore":0.5072487812208666,"totalDurationS":775905.225,"totalInputTokens":950614474,"totalOutputTokens":7394400,"totalCostUsd":463.87,"costSource":"db"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":297,"tasks":152,"splitTasks":152,"passes":82,"passRate":0.27960526315789475,"avgScore":0.5070206498203882,"totalDurationS":427119,"totalInputTokens":1244130625.6666667,"totalOutputTokens":5783219.833333333,"totalCostUsd":544.61,"costSource":"list"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":149,"tasks":149,"splitTasks":152,"passes":44,"passRate":0.2894736842105263,"avgScore":0.5037352082410917,"totalDurationS":239192,"totalInputTokens":2499272937,"totalOutputTokens":6752715,"totalCostUsd":390.61,"costSource":"list"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":152,"tasks":152,"splitTasks":152,"passes":46,"passRate":0.3026315789473684,"avgScore":0.49414814826021464,"totalDurationS":238042,"totalInputTokens":1435261861,"totalOutputTokens":4162374,"totalCostUsd":235.12,"costSource":"list"},{"split":"full/overall","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":150,"tasks":150,"splitTasks":152,"passes":39,"passRate":0.2565789473684211,"avgScore":0.4870141224330407,"totalDurationS":251985,"totalInputTokens":2740460142,"totalOutputTokens":10436301,"totalCostUsd":4340.24,"costSource":"official"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":299,"tasks":152,"splitTasks":152,"passes":82,"passRate":0.27631578947368424,"avgScore":0.484942264470657,"totalDurationS":314395.5,"totalInputTokens":822499178,"totalOutputTokens":3817073,"totalCostUsd":380.73,"costSource":"list"},{"split":"full/overall","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":299,"tasks":152,"splitTasks":152,"passes":80,"passRate":0.26644736842105265,"avgScore":0.47931391024591824,"totalDurationS":349652.5,"totalInputTokens":560480756,"totalOutputTokens":6366308.5,"totalCostUsd":601.69,"costSource":"db"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":298,"tasks":151,"splitTasks":152,"passes":77,"passRate":0.2598684210526316,"avgScore":0.465716312064728,"totalDurationS":354908.11950000003,"totalInputTokens":533875323.5,"totalOutputTokens":2793979.5,"totalCostUsd":261.53,"costSource":"db+list"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":152,"tasks":152,"splitTasks":152,"passes":37,"passRate":0.24342105263157895,"avgScore":0.46128766882143674,"totalDurationS":165192,"totalInputTokens":699354083,"totalOutputTokens":2559522,"totalCostUsd":127.52,"costSource":"list"},{"split":"full/overall","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":145,"tasks":145,"splitTasks":152,"passes":35,"passRate":0.23026315789473684,"avgScore":0.4578443243363864,"totalDurationS":128044.22844149194,"totalInputTokens":334305043,"totalOutputTokens":2340693,"totalCostUsd":309.77,"costSource":"db"},{"split":"full/overall","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":150,"tasks":150,"splitTasks":152,"passes":41,"passRate":0.26973684210526316,"avgScore":0.4514857743894153,"totalDurationS":645508,"totalInputTokens":1692408720,"totalOutputTokens":22067608,"totalCostUsd":3985,"costSource":"published"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":299,"tasks":151,"splitTasks":152,"passes":73,"passRate":0.2390350877192982,"avgScore":0.4509751802373446,"totalDurationS":270652.0256666667,"totalInputTokens":251962276.66666666,"totalOutputTokens":1269048.8333333333,"totalCostUsd":248.12,"costSource":"db+list"},{"split":"full/overall","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":438,"tasks":152,"splitTasks":152,"passes":110,"passRate":0.2445175438596491,"avgScore":0.44715784362305094,"totalDurationS":270900.40022482676,"totalInputTokens":489884949,"totalOutputTokens":3517360.8333333335,"totalCostUsd":415.59,"costSource":"db+list"},{"split":"full/overall","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":148,"tasks":148,"splitTasks":152,"passes":31,"passRate":0.20394736842105263,"avgScore":0.428847508157024,"totalDurationS":1000718.9020000002,"totalInputTokens":2742661908,"totalOutputTokens":14977273,"totalCostUsd":null,"costSource":null},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":297,"tasks":152,"splitTasks":152,"passes":69,"passRate":0.22697368421052633,"avgScore":0.4258635230185982,"totalDurationS":310012.218,"totalInputTokens":244642169.5,"totalOutputTokens":1565131.5,"totalCostUsd":128.23,"costSource":"db+list"},{"split":"full/overall","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":137,"tasks":137,"splitTasks":152,"passes":32,"passRate":0.21052631578947367,"avgScore":0.42487183710893694,"totalDurationS":229732.552303883,"totalInputTokens":429515271,"totalOutputTokens":4464514,"totalCostUsd":1899.32,"costSource":"official+adj"},{"split":"full/overall","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":151,"tasks":151,"splitTasks":152,"passes":34,"passRate":0.2236842105263158,"avgScore":0.4234878390395742,"totalDurationS":519320,"totalInputTokens":1209502455,"totalOutputTokens":16507476,"totalCostUsd":2815,"costSource":"published"},{"split":"full/overall","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":136,"tasks":136,"splitTasks":152,"passes":33,"passRate":0.21710526315789475,"avgScore":0.42072396960513175,"totalDurationS":297468.11566528457,"totalInputTokens":469259907,"totalOutputTokens":3279175,"totalCostUsd":446.52,"costSource":"db"},{"split":"full/overall","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":152,"tasks":144,"splitTasks":152,"passes":35,"passRate":0.2236842105263158,"avgScore":0.412877641079695,"totalDurationS":382422.5,"totalInputTokens":880037048.5,"totalOutputTokens":9436038.5,"totalCostUsd":2314.73,"costSource":"official"},{"split":"full/overall","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":146,"tasks":143,"splitTasks":152,"passes":30,"passRate":0.19078947368421054,"avgScore":0.4113172272326027,"totalDurationS":558819.5,"totalInputTokens":1903250155.5,"totalOutputTokens":8006212,"totalCostUsd":935.7,"costSource":"db"},{"split":"full/overall","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":146,"tasks":146,"splitTasks":152,"passes":31,"passRate":0.20394736842105263,"avgScore":0.41085406808572505,"totalDurationS":387747,"totalInputTokens":1291344387,"totalOutputTokens":7729473,"totalCostUsd":1085.62,"costSource":"db"},{"split":"full/overall","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":142,"tasks":139,"splitTasks":152,"passes":33,"passRate":0.2138157894736842,"avgScore":0.40680078557980925,"totalDurationS":211627.30808669614,"totalInputTokens":148061075,"totalOutputTokens":1687764,"totalCostUsd":173.52,"costSource":"list"},{"split":"full/overall","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":143,"tasks":143,"splitTasks":152,"passes":34,"passRate":0.2236842105263158,"avgScore":0.40677645580102734,"totalDurationS":298162,"totalInputTokens":1796865182,"totalOutputTokens":6432918,"totalCostUsd":1626,"costSource":"published"},{"split":"full/overall","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":143,"tasks":143,"splitTasks":152,"passes":28,"passRate":0.18421052631578946,"avgScore":0.4049605336355299,"totalDurationS":279527.28043104644,"totalInputTokens":1342066095,"totalOutputTokens":5568247,"totalCostUsd":1132.24,"costSource":"official"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":300,"tasks":152,"splitTasks":152,"passes":60,"passRate":0.20394736842105263,"avgScore":0.4024908249653849,"totalDurationS":275061.747,"totalInputTokens":171679764,"totalOutputTokens":1124088.5,"totalCostUsd":89.49,"costSource":"db+list"},{"split":"full/overall","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":149,"tasks":149,"splitTasks":152,"passes":28,"passRate":0.18421052631578946,"avgScore":0.39776664940409484,"totalDurationS":270641,"totalInputTokens":294404262,"totalOutputTokens":2853487,"totalCostUsd":357.68,"costSource":"db"},{"split":"full/overall","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":138,"tasks":138,"splitTasks":152,"passes":31,"passRate":0.20394736842105263,"avgScore":0.39480863219234935,"totalDurationS":280094,"totalInputTokens":338804815,"totalOutputTokens":2898338,"totalCostUsd":176.65,"costSource":"db+list"},{"split":"full/overall","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":139,"tasks":137,"splitTasks":152,"passes":30,"passRate":0.19736842105263158,"avgScore":0.3924651258147475,"totalDurationS":229751.49587275658,"totalInputTokens":234782616,"totalOutputTokens":2196372,"totalCostUsd":242.24,"costSource":"list"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":152,"tasks":152,"splitTasks":152,"passes":26,"passRate":0.17105263157894737,"avgScore":0.3850041500197,"totalDurationS":151697,"totalInputTokens":287164350,"totalOutputTokens":1082713,"totalCostUsd":57,"costSource":"list"},{"split":"full/overall","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":141,"tasks":141,"splitTasks":152,"passes":25,"passRate":0.16447368421052633,"avgScore":0.38312084275574215,"totalDurationS":489984,"totalInputTokens":452042179,"totalOutputTokens":3793251,"totalCostUsd":1837.79,"costSource":"official+adj"},{"split":"full/overall","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":179,"tasks":142,"splitTasks":152,"passes":40,"passRate":0.2050438596491228,"avgScore":0.3732607831603129,"totalDurationS":459960.9185098016,"totalInputTokens":488753872.1666667,"totalOutputTokens":7283825.166666667,"totalCostUsd":274.1,"costSource":"db"},{"split":"full/overall","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":152,"tasks":152,"splitTasks":152,"passes":26,"passRate":0.17105263157894737,"avgScore":0.3636965114654929,"totalDurationS":139211,"totalInputTokens":109294354,"totalOutputTokens":1270291,"totalCostUsd":146.61,"costSource":"db"},{"split":"full/overall","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":137,"tasks":137,"splitTasks":152,"passes":21,"passRate":0.13815789473684212,"avgScore":0.35803700118782017,"totalDurationS":153370.83306965837,"totalInputTokens":456438963,"totalOutputTokens":3700468,"totalCostUsd":1792.72,"costSource":"official+adj"},{"split":"full/overall","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":142,"tasks":141,"splitTasks":152,"passes":24,"passRate":0.15789473684210525,"avgScore":0.3521506822590183,"totalDurationS":446984.7452694551,"totalInputTokens":807329919,"totalOutputTokens":3963995.5,"totalCostUsd":1688.85,"costSource":"official+adj"},{"split":"full/overall","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":142,"tasks":142,"splitTasks":152,"passes":25,"passRate":0.16447368421052633,"avgScore":0.3270766092627965,"totalDurationS":332449,"totalInputTokens":1212565963,"totalOutputTokens":3542216,"totalCostUsd":2018.05,"costSource":"db+list+adj"},{"split":"full/overall","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":144,"tasks":144,"splitTasks":152,"passes":19,"passRate":0.125,"avgScore":0.3172013766706849,"totalDurationS":685102,"totalInputTokens":1673959024,"totalOutputTokens":20768691,"totalCostUsd":439.63,"costSource":"db"},{"split":"full/overall","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":105,"tasks":99,"splitTasks":152,"passes":22,"passRate":0.13486842105263158,"avgScore":0.31695780433940046,"totalDurationS":101780.76887404779,"totalInputTokens":352060264.5,"totalOutputTokens":2726292,"totalCostUsd":1356.25,"costSource":"official+adj"},{"split":"full/overall","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":142,"tasks":142,"splitTasks":152,"passes":18,"passRate":0.11842105263157894,"avgScore":0.3156864509879294,"totalDurationS":363579,"totalInputTokens":1382717830,"totalOutputTokens":17557559,"totalCostUsd":663.87,"costSource":"db+list"},{"split":"full/overall","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":152,"tasks":152,"splitTasks":152,"passes":18,"passRate":0.11842105263157894,"avgScore":0.31023834901975544,"totalDurationS":88490,"totalInputTokens":119921277,"totalOutputTokens":610291,"totalCostUsd":26.77,"costSource":"list"},{"split":"full/overall","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":149,"tasks":141,"splitTasks":152,"passes":22,"passRate":0.14144736842105263,"avgScore":0.2927265620525372,"totalDurationS":529548.719956005,"totalInputTokens":3369212141,"totalOutputTokens":3653426,"totalCostUsd":2968.62,"costSource":"db+adj"},{"split":"full/overall","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":143,"tasks":143,"splitTasks":152,"passes":18,"passRate":0.11842105263157894,"avgScore":0.2863832387982169,"totalDurationS":199675.9292053005,"totalInputTokens":1070761845,"totalOutputTokens":2049232,"totalCostUsd":335.05,"costSource":"db"},{"split":"full/overall","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":260,"tasks":140,"splitTasks":152,"passes":35,"passRate":0.11513157894736842,"avgScore":0.2813736456137783,"totalDurationS":607138.4432532396,"totalInputTokens":755773178.3333334,"totalOutputTokens":5896205,"totalCostUsd":439.78,"costSource":"db+list"},{"split":"full/overall","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":275,"tasks":146,"splitTasks":152,"passes":39,"passRate":0.12390350877192982,"avgScore":0.2762014846817647,"totalDurationS":470844.49271820637,"totalInputTokens":511717582.8333333,"totalOutputTokens":4746342.166666667,"totalCostUsd":273.05,"costSource":"db"},{"split":"full/overall","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":272,"tasks":146,"splitTasks":152,"passes":25,"passRate":0.08552631578947369,"avgScore":0.24606981345822615,"totalDurationS":484970.8091920079,"totalInputTokens":738910364.1666666,"totalOutputTokens":7027388.333333333,"totalCostUsd":253.85,"costSource":"db"},{"split":"full/overall","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":261,"tasks":146,"splitTasks":152,"passes":25,"passRate":0.08552631578947369,"avgScore":0.23555956574853623,"totalDurationS":386539.2838370383,"totalInputTokens":394850494.1666667,"totalOutputTokens":4001432.3333333335,"totalCostUsd":43.34,"costSource":"db+list"},{"split":"full/overall","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":241,"tasks":144,"splitTasks":152,"passes":25,"passRate":0.09210526315789473,"avgScore":0.21665039689683385,"totalDurationS":659868.3114792772,"totalInputTokens":295931464.5,"totalOutputTokens":6043559,"totalCostUsd":123.45,"costSource":"db+list"},{"split":"full/overall","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":149,"tasks":142,"splitTasks":152,"passes":11,"passRate":0.07236842105263158,"avgScore":0.21253888440188418,"totalDurationS":155198.84874021716,"totalInputTokens":223145635.66666666,"totalOutputTokens":2267515.6666666665,"totalCostUsd":284.6,"costSource":"list"},{"split":"full/overall","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":262,"tasks":145,"splitTasks":152,"passes":13,"passRate":0.04276315789473684,"avgScore":0.1577879873494589,"totalDurationS":284644.0846058948,"totalInputTokens":168652811,"totalOutputTokens":2745183,"totalCostUsd":80.18,"costSource":"db+list"},{"split":"full/overall","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":223,"tasks":146,"splitTasks":152,"passes":14,"passRate":0.05921052631578947,"avgScore":0.14187993275125252,"totalDurationS":520646.2217991107,"totalInputTokens":277209591.6666667,"totalOutputTokens":4379146.166666667,"totalCostUsd":26.74,"costSource":"db+list"},{"split":"full/overall","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":144,"tasks":142,"splitTasks":152,"passes":11,"passRate":0.07236842105263158,"avgScore":0.133367903588527,"totalDurationS":147936.49156970065,"totalInputTokens":206835017.5,"totalOutputTokens":3239534.5,"totalCostUsd":134.93,"costSource":"db"},{"split":"full/overall","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":143,"tasks":140,"splitTasks":152,"passes":7,"passRate":0.046052631578947366,"avgScore":0.1261454861416316,"totalDurationS":65674.81911909918,"totalInputTokens":55532219.5,"totalOutputTokens":512410,"totalCostUsd":174.28,"costSource":"db"},{"split":"licensed","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":11,"tasks":11,"splitTasks":11,"passes":2,"passRate":0.18181818181818182,"avgScore":0.44580146295868334,"totalDurationS":50004.460999999996,"totalInputTokens":200029803,"totalOutputTokens":757770,"totalCostUsd":101.79,"costSource":"db"},{"split":"licensed","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":11,"tasks":11,"splitTasks":11,"passes":1,"passRate":0.09090909090909091,"avgScore":0.3297649487170496,"totalDurationS":99345.342,"totalInputTokens":460330832,"totalOutputTokens":1067018,"totalCostUsd":166.16,"costSource":"db"},{"split":"licensed","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":10,"tasks":10,"splitTasks":11,"passes":1,"passRate":0.09090909090909091,"avgScore":0.2936469136497635,"totalDurationS":55546,"totalInputTokens":961315708,"totalOutputTokens":1273256,"totalCostUsd":1153.16,"costSource":"official"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":23,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.2746547921284107,"totalDurationS":61723.333333333336,"totalInputTokens":174136662.33333334,"totalOutputTokens":467479,"totalCostUsd":180.82,"costSource":"list"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":20,"tasks":11,"splitTasks":11,"passes":1,"passRate":0.09090909090909091,"avgScore":0.2728171107655029,"totalDurationS":91366,"totalInputTokens":96180035.66666667,"totalOutputTokens":392277.8333333333,"totalCostUsd":44.94,"costSource":"list"},{"split":"licensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.2646204586064638,"totalDurationS":59414.595,"totalInputTokens":107372149,"totalOutputTokens":472656,"totalCostUsd":148.01,"costSource":"official"},{"split":"licensed","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":11,"tasks":11,"splitTasks":11,"passes":1,"passRate":0.09090909090909091,"avgScore":0.25496571532732815,"totalDurationS":138843.963,"totalInputTokens":68988606,"totalOutputTokens":498389,"totalCostUsd":31.64,"costSource":"db"},{"split":"licensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.24051546646698893,"totalDurationS":47048.26999999999,"totalInputTokens":97571243,"totalOutputTokens":329677,"totalCostUsd":129.6,"costSource":"official"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":22,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.23849458053696015,"totalDurationS":55159.5,"totalInputTokens":92690197.5,"totalOutputTokens":190449,"totalCostUsd":94.47,"costSource":"list"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":21,"tasks":11,"splitTasks":11,"passes":1,"passRate":0.045454545454545456,"avgScore":0.23640261027768616,"totalDurationS":48776.5,"totalInputTokens":110572751,"totalOutputTokens":320037.5,"totalCostUsd":114.9,"costSource":"list"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":11,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.2343520785550317,"totalDurationS":22844,"totalInputTokens":56109934,"totalOutputTokens":143436,"totalCostUsd":11.06,"costSource":"list"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":21,"tasks":11,"splitTasks":11,"passes":1,"passRate":0.045454545454545456,"avgScore":0.23140343373334019,"totalDurationS":28205.5,"totalInputTokens":21887578.5,"totalOutputTokens":93987.5,"totalCostUsd":24.69,"costSource":"list"},{"split":"licensed","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":21,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.23112848158466556,"totalDurationS":62259,"totalInputTokens":79134957.5,"totalOutputTokens":621202,"totalCostUsd":78.93,"costSource":"db"},{"split":"licensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.2302228018064284,"totalDurationS":78490.022,"totalInputTokens":116149814,"totalOutputTokens":544837,"totalCostUsd":160.49,"costSource":"official"},{"split":"licensed","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.22847856547624412,"totalDurationS":31194.703,"totalInputTokens":133948890,"totalOutputTokens":664584,"totalCostUsd":25.69,"costSource":"official"},{"split":"licensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.22428600293867482,"totalDurationS":53442.983,"totalInputTokens":77798012,"totalOutputTokens":141930,"totalCostUsd":95.56,"costSource":"official"},{"split":"licensed","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":11,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.22245515154818696,"totalDurationS":91032,"totalInputTokens":59208218,"totalOutputTokens":212510,"totalCostUsd":65.73,"costSource":"db"},{"split":"licensed","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":11,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.22167032341406182,"totalDurationS":101694,"totalInputTokens":227246409,"totalOutputTokens":1695241,"totalCostUsd":288.39,"costSource":"published+task-ratio"},{"split":"licensed","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":26,"tasks":11,"splitTasks":11,"passes":1,"passRate":0.0303030303030303,"avgScore":0.22151974870087496,"totalDurationS":44609.951294866376,"totalInputTokens":71991083.5,"totalOutputTokens":346287,"totalCostUsd":76.54,"costSource":"db"},{"split":"licensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.22088561012161534,"totalDurationS":46410.01,"totalInputTokens":94803003,"totalOutputTokens":275420,"totalCostUsd":122.05,"costSource":"official"},{"split":"licensed","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":7,"tasks":7,"splitTasks":11,"passes":1,"passRate":0.09090909090909091,"avgScore":0.21759244620262602,"totalDurationS":10839.482776957002,"totalInputTokens":41313069,"totalOutputTokens":175293,"totalCostUsd":34.5,"costSource":"db"},{"split":"licensed","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":5,"tasks":5,"splitTasks":11,"passes":1,"passRate":0.09090909090909091,"avgScore":0.21559999999999999,"totalDurationS":26915.112756414877,"totalInputTokens":320986154,"totalOutputTokens":479276,"totalCostUsd":208.55,"costSource":"official"},{"split":"licensed","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.21253939393939394,"totalDurationS":61676.96299999999,"totalInputTokens":171792677,"totalOutputTokens":666638,"totalCostUsd":32.3,"costSource":"official"},{"split":"licensed","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.20981212121212123,"totalDurationS":127373.992,"totalInputTokens":253433815,"totalOutputTokens":802386,"totalCostUsd":null,"costSource":null},{"split":"licensed","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":22,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.20454787385590675,"totalDurationS":51418,"totalInputTokens":53183956.5,"totalOutputTokens":200989.5,"totalCostUsd":28.04,"costSource":"list"},{"split":"licensed","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.20143753235970452,"totalDurationS":89351.092,"totalInputTokens":441469903,"totalOutputTokens":1466623,"totalCostUsd":352.49,"costSource":"official"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":21,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.19829265389422995,"totalDurationS":57779.5,"totalInputTokens":50857945.5,"totalOutputTokens":196462.5,"totalCostUsd":49.79,"costSource":"list"},{"split":"licensed","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":9,"tasks":9,"splitTasks":11,"passes":1,"passRate":0.09090909090909091,"avgScore":0.19741818637555308,"totalDurationS":90651,"totalInputTokens":221376932,"totalOutputTokens":423610,"totalCostUsd":67.7,"costSource":"db"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":21,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.19554013940986384,"totalDurationS":25065.5,"totalInputTokens":31029753,"totalOutputTokens":114260.5,"totalCostUsd":16.92,"costSource":"list"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":22,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.19280668783242483,"totalDurationS":53991.5,"totalInputTokens":101601230,"totalOutputTokens":290736,"totalCostUsd":49.49,"costSource":"list"},{"split":"licensed","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":11,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.18756758749923322,"totalDurationS":103208,"totalInputTokens":74904373,"totalOutputTokens":1166124,"totalCostUsd":203.72,"costSource":"published+task-ratio"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":11,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.1855642458507263,"totalDurationS":11476,"totalInputTokens":63964976,"totalOutputTokens":85737,"totalCostUsd":12.28,"costSource":"list"},{"split":"licensed","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.17642727381542536,"totalDurationS":11674.388532931684,"totalInputTokens":76260216,"totalOutputTokens":255769,"totalCostUsd":233.89,"costSource":"official+adj"},{"split":"licensed","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.17438904837207417,"totalDurationS":41314,"totalInputTokens":27630691,"totalOutputTokens":370478,"totalCostUsd":28.31,"costSource":"db"},{"split":"licensed","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.16919639939223963,"totalDurationS":106893.535,"totalInputTokens":256972501,"totalOutputTokens":1676047,"totalCostUsd":80.31,"costSource":"db"},{"split":"licensed","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":9,"tasks":9,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.1686806428594572,"totalDurationS":93969.19600000001,"totalInputTokens":472094630,"totalOutputTokens":1398846,"totalCostUsd":355.7,"costSource":"official"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":11,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.15451296049520938,"totalDurationS":48790,"totalInputTokens":129505530,"totalOutputTokens":285267,"totalCostUsd":22.47,"costSource":"list"},{"split":"licensed","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":9,"tasks":9,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.1509848484848485,"totalDurationS":52399.460999999996,"totalInputTokens":283708787,"totalOutputTokens":617241,"totalCostUsd":197.45,"costSource":"official"},{"split":"licensed","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.14881818181818182,"totalDurationS":87422.245,"totalInputTokens":439388124,"totalOutputTokens":856207,"totalCostUsd":325.24,"costSource":"official"},{"split":"licensed","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.14677272727272728,"totalDurationS":74073.509,"totalInputTokens":310841455,"totalOutputTokens":360100,"totalCostUsd":214.21,"costSource":"official"},{"split":"licensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":10,"tasks":10,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.14282709627861873,"totalDurationS":38724.141,"totalInputTokens":87352750,"totalOutputTokens":146624,"totalCostUsd":104.74,"costSource":"official"},{"split":"licensed","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":5,"tasks":5,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.14213636363636362,"totalDurationS":23501.70769077503,"totalInputTokens":65402260,"totalOutputTokens":195271,"totalCostUsd":52.38,"costSource":"db"},{"split":"licensed","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.13946830391958281,"totalDurationS":19954.802037291927,"totalInputTokens":112444567,"totalOutputTokens":549497,"totalCostUsd":335.13,"costSource":"official+adj"},{"split":"licensed","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":6,"tasks":6,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.12848904115546353,"totalDurationS":42157.90135035687,"totalInputTokens":19445057,"totalOutputTokens":86437,"totalCostUsd":16.17,"costSource":"list"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":8,"tasks":8,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.1268451543325831,"totalDurationS":39399,"totalInputTokens":100638252,"totalOutputTokens":306689,"totalCostUsd":19.08,"costSource":"list"},{"split":"licensed","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":5,"tasks":5,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.12105454545454544,"totalDurationS":22156.88134723599,"totalInputTokens":20087045,"totalOutputTokens":104770,"totalCostUsd":17.28,"costSource":"list"},{"split":"licensed","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":11,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.11761216637194266,"totalDurationS":31197,"totalInputTokens":13106049,"totalOutputTokens":93375,"totalCostUsd":18.71,"costSource":"db"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":22,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.11405527444844456,"totalDurationS":24853,"totalInputTokens":18146765,"totalOutputTokens":73848,"totalCostUsd":10.07,"costSource":"list"},{"split":"licensed","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":8,"tasks":8,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.1083130564079132,"totalDurationS":30318,"totalInputTokens":225487387,"totalOutputTokens":811747,"totalCostUsd":117.67,"costSource":"published+task-ratio"},{"split":"licensed","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":4,"tasks":4,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.09358050212076585,"totalDurationS":54692,"totalInputTokens":72521956,"totalOutputTokens":359088,"totalCostUsd":null,"costSource":null},{"split":"licensed","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":9,"tasks":6,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.08532931528060012,"totalDurationS":79704.71851659058,"totalInputTokens":163706540.5,"totalOutputTokens":765808,"totalCostUsd":90.81,"costSource":"db"},{"split":"licensed","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":11,"tasks":11,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.08178194518550498,"totalDurationS":10610,"totalInputTokens":17611367,"totalOutputTokens":48073,"totalCostUsd":4.31,"costSource":"list"},{"split":"licensed","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":5,"tasks":5,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.08,"totalDurationS":23712,"totalInputTokens":144741842,"totalOutputTokens":380341,"totalCostUsd":509.28,"costSource":"official+adj"},{"split":"licensed","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.07636363636363636,"totalDurationS":26224.622477491153,"totalInputTokens":38055264,"totalOutputTokens":251023,"totalCostUsd":17.87,"costSource":"db"},{"split":"licensed","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":6,"tasks":6,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.07272727272727274,"totalDurationS":58717,"totalInputTokens":134516414,"totalOutputTokens":529925,"totalCostUsd":486.11,"costSource":"official"},{"split":"licensed","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":5,"tasks":5,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.06488004334475987,"totalDurationS":43145.14858130082,"totalInputTokens":85179111,"totalOutputTokens":155544,"totalCostUsd":193.55,"costSource":"official+adj"},{"split":"licensed","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":10,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.06469090909090909,"totalDurationS":46421.8629133185,"totalInputTokens":120729225.5,"totalOutputTokens":575606.5,"totalCostUsd":40.36,"costSource":"db"},{"split":"licensed","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":4,"tasks":4,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.06468889570193674,"totalDurationS":2505.957411190262,"totalInputTokens":7226933,"totalOutputTokens":83461,"totalCostUsd":31.19,"costSource":"official+adj"},{"split":"licensed","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":4,"tasks":4,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.06181818181818182,"totalDurationS":12609,"totalInputTokens":52332507,"totalOutputTokens":178057,"totalCostUsd":26.61,"costSource":"db"},{"split":"licensed","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.05818181818181818,"totalDurationS":15394,"totalInputTokens":53032368,"totalOutputTokens":152897,"totalCostUsd":75.08,"costSource":"db+adj"},{"split":"licensed","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.05454545454545454,"totalDurationS":79683.10143035022,"totalInputTokens":455406090,"totalOutputTokens":203960,"totalCostUsd":344.43,"costSource":"db+adj"},{"split":"licensed","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.05454545454545454,"totalDurationS":96458.79918224877,"totalInputTokens":2680382,"totalOutputTokens":77435,"totalCostUsd":1.85,"costSource":"db+list"},{"split":"licensed","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":10,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.04933571143251942,"totalDurationS":30323.92184410304,"totalInputTokens":52500160,"totalOutputTokens":181309.5,"totalCostUsd":4.85,"costSource":"db"},{"split":"licensed","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.04727272727272727,"totalDurationS":78051.486962114,"totalInputTokens":2230363,"totalOutputTokens":630683,"totalCostUsd":1.43,"costSource":"list"},{"split":"licensed","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.04363636363636363,"totalDurationS":50592,"totalInputTokens":137394982,"totalOutputTokens":540062,"totalCostUsd":60.52,"costSource":"db+list"},{"split":"licensed","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.041695254559251674,"totalDurationS":82357.47953877086,"totalInputTokens":70118711,"totalOutputTokens":504819,"totalCostUsd":32.38,"costSource":"db"},{"split":"licensed","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":6,"tasks":6,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.03272727272727272,"totalDurationS":43091.204194458005,"totalInputTokens":299479453,"totalOutputTokens":328146,"totalCostUsd":87.74,"costSource":"db"},{"split":"licensed","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":10,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.010909090909090908,"totalDurationS":32322.73259043986,"totalInputTokens":8234827.5,"totalOutputTokens":141910,"totalCostUsd":4.92,"costSource":"db+list"},{"split":"licensed","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":7,"tasks":6,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.010909090909090908,"totalDurationS":100.86548943573143,"totalInputTokens":null,"totalOutputTokens":null,"totalCostUsd":null,"costSource":null},{"split":"licensed","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":8,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.010909090909090908,"totalDurationS":40957.625895123885,"totalInputTokens":27131876,"totalOutputTokens":168389,"totalCostUsd":21.21,"costSource":"db"},{"split":"licensed","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":7,"tasks":7,"splitTasks":11,"passes":0,"passRate":0,"avgScore":0.010909090909090908,"totalDurationS":134.47499645897187,"totalInputTokens":null,"totalOutputTokens":null,"totalCostUsd":null,"costSource":null},{"split":"linux_only","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":105,"tasks":105,"splitTasks":105,"passes":35,"passRate":0.3333333333333333,"avgScore":0.614396632945848,"totalDurationS":253943.00500000006,"totalInputTokens":227495188,"totalOutputTokens":3730102,"totalCostUsd":506.68,"costSource":"official"},{"split":"linux_only","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":105,"tasks":105,"splitTasks":105,"passes":32,"passRate":0.3047619047619048,"avgScore":0.5915284408274188,"totalDurationS":144043.66700000002,"totalInputTokens":202380492,"totalOutputTokens":1603492,"totalCostUsd":339.36,"costSource":"official"},{"split":"linux_only","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":105,"tasks":105,"splitTasks":105,"passes":32,"passRate":0.3047619047619048,"avgScore":0.5896171865541988,"totalDurationS":182928.66499999998,"totalInputTokens":237680280,"totalOutputTokens":2688849,"totalCostUsd":451.98,"costSource":"official"},{"split":"linux_only","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":105,"tasks":105,"splitTasks":105,"passes":31,"passRate":0.29523809523809524,"avgScore":0.588957698678903,"totalDurationS":165218.36999999997,"totalInputTokens":206021273,"totalOutputTokens":2192931,"totalCostUsd":385.59,"costSource":"official"},{"split":"linux_only","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":105,"tasks":105,"splitTasks":105,"passes":35,"passRate":0.3333333333333333,"avgScore":0.57461709673845,"totalDurationS":135103.81200000003,"totalInputTokens":1290490494,"totalOutputTokens":7656491,"totalCostUsd":256.24,"costSource":"official"},{"split":"linux_only","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":105,"tasks":105,"splitTasks":105,"passes":31,"passRate":0.29523809523809524,"avgScore":0.5728954803470988,"totalDurationS":155694.44800000003,"totalInputTokens":1251841114,"totalOutputTokens":7168977,"totalCostUsd":248.79,"costSource":"official"},{"split":"linux_only","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":104,"tasks":104,"splitTasks":105,"passes":31,"passRate":0.29523809523809524,"avgScore":0.572695535485544,"totalDurationS":265411.2540000001,"totalInputTokens":819473457,"totalOutputTokens":6102567,"totalCostUsd":856.64,"costSource":"official"},{"split":"linux_only","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":105,"tasks":105,"splitTasks":105,"passes":28,"passRate":0.26666666666666666,"avgScore":0.5615036336389002,"totalDurationS":291094.98500000004,"totalInputTokens":1137627881,"totalOutputTokens":8904002,"totalCostUsd":1151.91,"costSource":"official"},{"split":"linux_only","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":105,"tasks":105,"splitTasks":105,"passes":30,"passRate":0.2857142857142857,"avgScore":0.5614557684928161,"totalDurationS":120336.52500000001,"totalInputTokens":149537384,"totalOutputTokens":1084995,"totalCostUsd":249.44,"costSource":"official"},{"split":"linux_only","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":105,"tasks":105,"splitTasks":105,"passes":29,"passRate":0.2761904761904762,"avgScore":0.5481996358460363,"totalDurationS":209442.814,"totalInputTokens":582458409,"totalOutputTokens":3882695,"totalCostUsd":588.86,"costSource":"official"},{"split":"linux_only","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":105,"tasks":105,"splitTasks":105,"passes":27,"passRate":0.2571428571428571,"avgScore":0.5481642165516963,"totalDurationS":113593.63399999995,"totalInputTokens":344592281,"totalOutputTokens":1092832,"totalCostUsd":452.79,"costSource":"official"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":209,"tasks":105,"splitTasks":105,"passes":60,"passRate":0.2857142857142857,"avgScore":0.5363939737297058,"totalDurationS":179145.1965,"totalInputTokens":443472815.3333333,"totalOutputTokens":2515905.5,"totalCostUsd":446.38,"costSource":"db+list"},{"split":"linux_only","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":104,"tasks":104,"splitTasks":105,"passes":30,"passRate":0.2857142857142857,"avgScore":0.5337049627977294,"totalDurationS":310740.245,"totalInputTokens":1211321313,"totalOutputTokens":9761091,"totalCostUsd":1272.47,"costSource":"official"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":207,"tasks":105,"splitTasks":105,"passes":57,"passRate":0.2857142857142857,"avgScore":0.531374869029037,"totalDurationS":171176.44199999998,"totalInputTokens":300085777.5,"totalOutputTokens":1422241,"totalCostUsd":279.31,"costSource":"db+list"},{"split":"linux_only","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":102,"tasks":102,"splitTasks":105,"passes":29,"passRate":0.2761904761904762,"avgScore":0.5278637305133695,"totalDurationS":393848.4819999999,"totalInputTokens":465187955,"totalOutputTokens":4686442,"totalCostUsd":251.07,"costSource":"db"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":105,"tasks":105,"splitTasks":105,"passes":30,"passRate":0.2857142857142857,"avgScore":0.5238739062483173,"totalDurationS":127293,"totalInputTokens":1605477710,"totalOutputTokens":4271202,"totalCostUsd":246.38,"costSource":"list"},{"split":"linux_only","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":104,"tasks":104,"splitTasks":105,"passes":26,"passRate":0.24761904761904763,"avgScore":0.5233151908037507,"totalDurationS":253030.36200000008,"totalInputTokens":348983748,"totalOutputTokens":2230474,"totalCostUsd":404.52,"costSource":"official"},{"split":"linux_only","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":102,"tasks":102,"splitTasks":105,"passes":29,"passRate":0.2761904761904762,"avgScore":0.5195649529905552,"totalDurationS":368089.04900000006,"totalInputTokens":604383029,"totalOutputTokens":5019776,"totalCostUsd":304.99,"costSource":"db"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":206,"tasks":105,"splitTasks":105,"passes":55,"passRate":0.2714285714285714,"avgScore":0.512155695633506,"totalDurationS":184402.47,"totalInputTokens":359092352,"totalOutputTokens":1936844.5,"totalCostUsd":343.41,"costSource":"db+list"},{"split":"linux_only","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":102,"tasks":102,"splitTasks":105,"passes":26,"passRate":0.24761904761904763,"avgScore":0.5112101968778014,"totalDurationS":407974.578,"totalInputTokens":559879430,"totalOutputTokens":6819773,"totalCostUsd":249.16,"costSource":"db"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":211,"tasks":105,"splitTasks":105,"passes":54,"passRate":0.26666666666666666,"avgScore":0.5094898978576776,"totalDurationS":188101.37800000003,"totalInputTokens":609639112.8333334,"totalOutputTokens":3521398.8333333335,"totalCostUsd":597.25,"costSource":"db+list"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":105,"tasks":105,"splitTasks":105,"passes":31,"passRate":0.29523809523809524,"avgScore":0.507344624718011,"totalDurationS":89570,"totalInputTokens":910676386,"totalOutputTokens":2836040,"totalCostUsd":143.63,"costSource":"list"},{"split":"linux_only","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":104,"tasks":104,"splitTasks":105,"passes":27,"passRate":0.2571428571428571,"avgScore":0.5059063643458925,"totalDurationS":186556.86099999992,"totalInputTokens":247602114,"totalOutputTokens":3321922,"totalCostUsd":139.15,"costSource":"db"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":206,"tasks":105,"splitTasks":105,"passes":53,"passRate":0.2571428571428571,"avgScore":0.5012199103904947,"totalDurationS":211284.5,"totalInputTokens":843825855.5,"totalOutputTokens":3883120,"totalCostUsd":357.6,"costSource":"list"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":206,"tasks":105,"splitTasks":105,"passes":54,"passRate":0.2619047619047619,"avgScore":0.4936421663563447,"totalDurationS":176760,"totalInputTokens":528038236.5,"totalOutputTokens":2578406,"totalCostUsd":234.69,"costSource":"list"},{"split":"linux_only","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":208,"tasks":105,"splitTasks":105,"passes":56,"passRate":0.2714285714285714,"avgScore":0.49235206278939025,"totalDurationS":171263.5,"totalInputTokens":357080347,"totalOutputTokens":4337017,"totalCostUsd":384.51,"costSource":"db"},{"split":"linux_only","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":105,"tasks":105,"splitTasks":105,"passes":25,"passRate":0.23809523809523808,"avgScore":0.4845098377095127,"totalDurationS":124476,"totalInputTokens":900239978,"totalOutputTokens":6378495,"totalCostUsd":1662.85,"costSource":"official"},{"split":"linux_only","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":103,"tasks":103,"splitTasks":105,"passes":26,"passRate":0.24761904761904763,"avgScore":0.480849060167781,"totalDurationS":60234.271691576985,"totalInputTokens":77021220,"totalOutputTokens":1313359,"totalCostUsd":108.61,"costSource":"db"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":105,"tasks":105,"splitTasks":105,"passes":26,"passRate":0.24761904761904763,"avgScore":0.47755529230158056,"totalDurationS":60549,"totalInputTokens":413704161,"totalOutputTokens":1707402,"totalCostUsd":72.92,"costSource":"list"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":207,"tasks":104,"splitTasks":105,"passes":51,"passRate":0.24285714285714285,"avgScore":0.4688643981010808,"totalDurationS":167006.6195,"totalInputTokens":297435267,"totalOutputTokens":1832875,"totalCostUsd":144.1,"costSource":"db+list"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":205,"tasks":104,"splitTasks":105,"passes":50,"passRate":0.23809523809523808,"avgScore":0.4681714417182331,"totalDurationS":161026.859,"totalInputTokens":140230593.5,"totalOutputTokens":820328.5,"totalCostUsd":132.28,"costSource":"db+list"},{"split":"linux_only","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":101,"tasks":101,"splitTasks":105,"passes":26,"passRate":0.24761904761904763,"avgScore":0.4605257773323447,"totalDurationS":113408.57987576415,"totalInputTokens":211187431,"totalOutputTokens":2152504,"totalCostUsd":218.69,"costSource":"db"},{"split":"linux_only","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":109,"tasks":103,"splitTasks":105,"passes":24,"passRate":0.22380952380952382,"avgScore":0.4575886915040092,"totalDurationS":250989,"totalInputTokens":301356111.5,"totalOutputTokens":6923181.5,"totalCostUsd":880.25,"costSource":"official"},{"split":"linux_only","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":96,"tasks":96,"splitTasks":105,"passes":24,"passRate":0.22857142857142856,"avgScore":0.45680671377661547,"totalDurationS":89632.5721885981,"totalInputTokens":207544892,"totalOutputTokens":2506674,"totalCostUsd":1044.57,"costSource":"official+adj"},{"split":"linux_only","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":310,"tasks":105,"splitTasks":105,"passes":74,"passRate":0.2365079365079365,"avgScore":0.4560896833299899,"totalDurationS":112697.86125335163,"totalInputTokens":292732648,"totalOutputTokens":2111892,"totalCostUsd":221.27,"costSource":"db+list"},{"split":"linux_only","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":102,"tasks":102,"splitTasks":105,"passes":25,"passRate":0.23809523809523808,"avgScore":0.4460039363451024,"totalDurationS":211355,"totalInputTokens":1098101909,"totalOutputTokens":4222336,"totalCostUsd":1015.69,"costSource":"published"},{"split":"linux_only","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":104,"tasks":104,"splitTasks":105,"passes":25,"passRate":0.23809523809523808,"avgScore":0.4415980756094993,"totalDurationS":231492,"totalInputTokens":1190914196,"totalOutputTokens":6337297,"totalCostUsd":980.79,"costSource":"db"},{"split":"linux_only","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":104,"tasks":104,"splitTasks":105,"passes":27,"passRate":0.2571428571428571,"avgScore":0.4406278923915453,"totalDurationS":399408,"totalInputTokens":642239869,"totalOutputTokens":15272399,"totalCostUsd":1953.22,"costSource":"published"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":207,"tasks":105,"splitTasks":105,"passes":47,"passRate":0.22380952380952382,"avgScore":0.439100891470296,"totalDurationS":191221.218,"totalInputTokens":125054108,"totalOutputTokens":1031431,"totalCostUsd":64.73,"costSource":"db+list"},{"split":"linux_only","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":104,"tasks":104,"splitTasks":105,"passes":20,"passRate":0.19047619047619047,"avgScore":0.4354068132927283,"totalDurationS":583968.235,"totalInputTokens":1627349109,"totalOutputTokens":10241576,"totalCostUsd":null,"costSource":null},{"split":"linux_only","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":100,"tasks":100,"splitTasks":105,"passes":24,"passRate":0.22857142857142856,"avgScore":0.43427017991504974,"totalDurationS":52191.603746200475,"totalInputTokens":68450446,"totalOutputTokens":1079925,"totalCostUsd":97.48,"costSource":"list"},{"split":"linux_only","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":103,"tasks":103,"splitTasks":105,"passes":21,"passRate":0.2,"avgScore":0.4326975564273962,"totalDurationS":159298.15374917473,"totalInputTokens":389612585,"totalOutputTokens":2906411,"totalCostUsd":415.55,"costSource":"official"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":208,"tasks":105,"splitTasks":105,"passes":43,"passRate":0.20476190476190476,"avgScore":0.42524049731525787,"totalDurationS":164807.247,"totalInputTokens":99257724.5,"totalOutputTokens":779045,"totalCostUsd":50.45,"costSource":"db+list"},{"split":"linux_only","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":101,"tasks":101,"splitTasks":105,"passes":20,"passRate":0.19047619047619047,"avgScore":0.42206259863995366,"totalDurationS":216579,"totalInputTokens":153192576,"totalOutputTokens":1763306,"totalCostUsd":81,"costSource":"db+list"},{"split":"linux_only","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":104,"tasks":101,"splitTasks":105,"passes":21,"passRate":0.19047619047619047,"avgScore":0.42145206902080673,"totalDurationS":317485.5,"totalInputTokens":1068611536.5,"totalOutputTokens":5782321,"totalCostUsd":601.58,"costSource":"db"},{"split":"linux_only","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":104,"tasks":104,"splitTasks":105,"passes":21,"passRate":0.2,"avgScore":0.42142958861655383,"totalDurationS":304614,"totalInputTokens":640997605,"totalOutputTokens":11872346,"totalCostUsd":1713.22,"costSource":"published"},{"split":"linux_only","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":130,"tasks":101,"splitTasks":105,"passes":32,"passRate":0.2253968253968254,"avgScore":0.4184820514506088,"totalDurationS":180443.07324218247,"totalInputTokens":285789922,"totalOutputTokens":4866454.666666667,"totalCostUsd":169.13,"costSource":"db"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":105,"tasks":105,"splitTasks":105,"passes":19,"passRate":0.18095238095238095,"avgScore":0.41185751264390447,"totalDurationS":48741,"totalInputTokens":127297515,"totalOutputTokens":721721,"totalCostUsd":25.06,"costSource":"list"},{"split":"linux_only","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":102,"tasks":102,"splitTasks":105,"passes":18,"passRate":0.17142857142857143,"avgScore":0.4089984699607975,"totalDurationS":324041,"totalInputTokens":112447742,"totalOutputTokens":1784448,"totalCostUsd":566.31,"costSource":"official+adj"},{"split":"linux_only","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":101,"tasks":101,"splitTasks":105,"passes":21,"passRate":0.2,"avgScore":0.40481898174638836,"totalDurationS":134836.59417068138,"totalInputTokens":117031110,"totalOutputTokens":1468511,"totalCostUsd":135.91,"costSource":"list"},{"split":"linux_only","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":103,"tasks":103,"splitTasks":105,"passes":18,"passRate":0.17142857142857143,"avgScore":0.39445811616626686,"totalDurationS":95269,"totalInputTokens":157904128,"totalOutputTokens":1928277,"totalCostUsd":194.65,"costSource":"db"},{"split":"linux_only","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":105,"tasks":105,"splitTasks":105,"passes":19,"passRate":0.18095238095238095,"avgScore":0.394105932064375,"totalDurationS":59135,"totalInputTokens":75852337,"totalOutputTokens":901935,"totalCostUsd":96.38,"costSource":"db"},{"split":"linux_only","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":96,"tasks":96,"splitTasks":105,"passes":16,"passRate":0.1523809523809524,"avgScore":0.3890574125005675,"totalDurationS":92839.4148778622,"totalInputTokens":280978346,"totalOutputTokens":2723233,"totalCostUsd":1164.8,"costSource":"official+adj"},{"split":"linux_only","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":104,"tasks":103,"splitTasks":105,"passes":18,"passRate":0.17142857142857143,"avgScore":0.38739364141550475,"totalDurationS":192542.93685384613,"totalInputTokens":516245034,"totalOutputTokens":2766369.5,"totalCostUsd":959.57,"costSource":"official+adj"},{"split":"linux_only","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":101,"tasks":101,"splitTasks":105,"passes":19,"passRate":0.18095238095238095,"avgScore":0.3717262877253931,"totalDurationS":188815,"totalInputTokens":450754861,"totalOutputTokens":2390671,"totalCostUsd":1009.61,"costSource":"db+list+adj"},{"split":"linux_only","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":74,"tasks":70,"splitTasks":105,"passes":17,"passRate":0.1523809523809524,"avgScore":0.3469339382470838,"totalDurationS":69448.19969177898,"totalInputTokens":176866012,"totalOutputTokens":1651850,"totalCostUsd":709.97,"costSource":"official+adj"},{"split":"linux_only","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":102,"tasks":102,"splitTasks":105,"passes":14,"passRate":0.13333333333333333,"avgScore":0.34638125058546504,"totalDurationS":123757,"totalInputTokens":1014954271,"totalOutputTokens":15755710,"totalCostUsd":534.27,"costSource":"db"},{"split":"linux_only","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":105,"tasks":105,"splitTasks":105,"passes":12,"passRate":0.11428571428571428,"avgScore":0.3382578991413626,"totalDurationS":352786,"totalInputTokens":1383584629,"totalOutputTokens":18413388,"totalCostUsd":439.63,"costSource":"db"},{"split":"linux_only","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":103,"tasks":103,"splitTasks":105,"passes":14,"passRate":0.13333333333333333,"avgScore":0.33810777616126964,"totalDurationS":95462.72998667358,"totalInputTokens":541326506,"totalOutputTokens":1131556,"totalCostUsd":168.38,"costSource":"db"},{"split":"linux_only","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":105,"tasks":105,"splitTasks":105,"passes":12,"passRate":0.11428571428571428,"avgScore":0.3361045019913022,"totalDurationS":33091,"totalInputTokens":56323564,"totalOutputTokens":407087,"totalCostUsd":12.85,"costSource":"list"},{"split":"linux_only","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":108,"tasks":100,"splitTasks":105,"passes":17,"passRate":0.15714285714285714,"avgScore":0.32433446158178597,"totalDurationS":238983.29079494995,"totalInputTokens":1367870276,"totalOutputTokens":2349345,"totalCostUsd":1303.46,"costSource":"db+adj"},{"split":"linux_only","harness":"hermes","model":"claude-sonnet-4-6","harnessVariant":null,"runs":248,"tasks":96,"splitTasks":105,"passes":36,"passRate":0.13174603174603172,"avgScore":0.3203670919271656,"totalDurationS":90692.90777800296,"totalInputTokens":195596773.66666666,"totalOutputTokens":2001710.3333333333,"totalCostUsd":436.6,"costSource":"official"},{"split":"linux_only","harness":"openclaw","model":"claude-sonnet-4-6","harnessVariant":null,"runs":88,"tasks":88,"splitTasks":105,"passes":12,"passRate":0.11428571428571428,"avgScore":0.3164026085498648,"totalDurationS":121852.04607221007,"totalInputTokens":247046472,"totalOutputTokens":1875276,"totalCostUsd":181.33,"costSource":"official"},{"split":"linux_only","harness":"terminus_2","model":"claude-sonnet-4-6","harnessVariant":null,"runs":179,"tasks":97,"splitTasks":105,"passes":24,"passRate":0.11904761904761904,"avgScore":0.30942664987397717,"totalDurationS":262860.15114356764,"totalInputTokens":760392746.5,"totalOutputTokens":3129737,"totalCostUsd":319.72,"costSource":"official"},{"split":"linux_only","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":213,"tasks":104,"splitTasks":105,"passes":32,"passRate":0.14126984126984127,"avgScore":0.30841640658848457,"totalDurationS":202301.7898809551,"totalInputTokens":312819738.8333333,"totalOutputTokens":3293259.1666666665,"totalCostUsd":161.39,"costSource":"db"},{"split":"linux_only","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":193,"tasks":100,"splitTasks":105,"passes":27,"passRate":0.12857142857142856,"avgScore":0.3078167601947899,"totalDurationS":266197.7125626944,"totalInputTokens":361003727.3333333,"totalOutputTokens":3257192,"totalCostUsd":212.77,"costSource":"db+list"},{"split":"linux_only","harness":"forgecode","model":"claude-sonnet-4-6","harnessVariant":null,"runs":244,"tasks":97,"splitTasks":105,"passes":38,"passRate":0.13333333333333336,"avgScore":0.28997250926121826,"totalDurationS":185485.77300154004,"totalInputTokens":136530209.83333334,"totalOutputTokens":1726369,"totalCostUsd":100.05,"costSource":"official"},{"split":"linux_only","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":201,"tasks":104,"splitTasks":105,"passes":21,"passRate":0.10476190476190476,"avgScore":0.2895843637929504,"totalDurationS":224862.70664021675,"totalInputTokens":366815218.1666667,"totalOutputTokens":4436483.5,"totalCostUsd":127.87,"costSource":"db"},{"split":"linux_only","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":197,"tasks":104,"splitTasks":105,"passes":20,"passRate":0.1,"avgScore":0.26465217947397845,"totalDurationS":185037.9774775899,"totalInputTokens":286441573.5,"totalOutputTokens":3005020.6666666665,"totalCostUsd":31.54,"costSource":"db+list"},{"split":"linux_only","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":106,"tasks":101,"splitTasks":105,"passes":9,"passRate":0.08571428571428572,"avgScore":0.2587004052874691,"totalDurationS":130308.89312641587,"totalInputTokens":160976232.16666666,"totalOutputTokens":1691379.1666666667,"totalCostUsd":205.45,"costSource":"list"},{"split":"linux_only","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":188,"tasks":104,"splitTasks":105,"passes":16,"passRate":0.08095238095238096,"avgScore":0.2123825941816749,"totalDurationS":322265.0739102186,"totalInputTokens":222945194.5,"totalOutputTokens":4427429,"totalCostUsd":90.85,"costSource":"db+list"},{"split":"linux_only","harness":"openhands","model":"claude-sonnet-4-6","harnessVariant":null,"runs":285,"tasks":97,"splitTasks":105,"passes":28,"passRate":0.09047619047619047,"avgScore":0.19774111108214873,"totalDurationS":128828.19181078624,"totalInputTokens":349872550.5,"totalOutputTokens":4376178.5,"totalCostUsd":242.67,"costSource":"official"},{"split":"linux_only","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":196,"tasks":104,"splitTasks":105,"passes":9,"passRate":0.04285714285714286,"avgScore":0.1783785050309947,"totalDurationS":130058.32605030174,"totalInputTokens":135849770.5,"totalOutputTokens":2118467,"totalCostUsd":60.74,"costSource":"db+list"},{"split":"linux_only","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":101,"tasks":100,"splitTasks":105,"passes":5,"passRate":0.047619047619047616,"avgScore":0.1605153704145524,"totalDurationS":61339.89233026502,"totalInputTokens":52877211.5,"totalOutputTokens":471635,"totalCostUsd":165.71,"costSource":"db"},{"split":"linux_only","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":167,"tasks":104,"splitTasks":105,"passes":9,"passRate":0.05714285714285714,"avgScore":0.1464903265101336,"totalDurationS":190567.1761067583,"totalInputTokens":242674106.16666666,"totalOutputTokens":3192715.3333333335,"totalCostUsd":22.15,"costSource":"db+list"},{"split":"linux_only","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":102,"tasks":101,"splitTasks":105,"passes":7,"passRate":0.06666666666666667,"avgScore":0.13116963841633533,"totalDurationS":39510.33435794874,"totalInputTokens":85353349,"totalOutputTokens":1849844,"totalCostUsd":62.4,"costSource":"db"},{"split":"unlicensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":141,"tasks":141,"splitTasks":141,"passes":52,"passRate":0.36879432624113473,"avgScore":0.6208260417791966,"totalDurationS":448067.04299999995,"totalInputTokens":394105877,"totalOutputTokens":5225794,"totalCostUsd":787.03,"costSource":"official"},{"split":"unlicensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":141,"tasks":141,"splitTasks":141,"passes":49,"passRate":0.3475177304964539,"avgScore":0.6077671854401283,"totalDurationS":287561.2380000002,"totalInputTokens":371380020,"totalOutputTokens":3717082,"totalCostUsd":672.34,"costSource":"official"},{"split":"unlicensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":141,"tasks":141,"splitTasks":141,"passes":48,"passRate":0.3404255319148936,"avgScore":0.6041127316087272,"totalDurationS":278749.57200000004,"totalInputTokens":322713382,"totalOutputTokens":3045094,"totalCostUsd":575.61,"costSource":"official"},{"split":"unlicensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":141,"tasks":141,"splitTasks":141,"passes":49,"passRate":0.3475177304964539,"avgScore":0.603927171087911,"totalDurationS":215282.77100000004,"totalInputTokens":312451511,"totalOutputTokens":2158009,"totalCostUsd":501.86,"costSource":"official"},{"split":"unlicensed","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":141,"tasks":141,"splitTasks":141,"passes":49,"passRate":0.3475177304964539,"avgScore":0.5844936386105954,"totalDurationS":228558.01299999992,"totalInputTokens":1959131229,"totalOutputTokens":11156960,"totalCostUsd":395.79,"costSource":"official"},{"split":"unlicensed","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":139,"tasks":139,"splitTasks":141,"passes":48,"passRate":0.3404255319148936,"avgScore":0.5834754211468836,"totalDurationS":375141.539,"totalInputTokens":1352781217,"totalOutputTokens":9262715,"totalCostUsd":1312.67,"costSource":"official"},{"split":"unlicensed","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":141,"tasks":141,"splitTasks":141,"passes":46,"passRate":0.3262411347517731,"avgScore":0.5828994280632535,"totalDurationS":484182.8020000001,"totalInputTokens":2035626608,"totalOutputTokens":14188637,"totalCostUsd":1926,"costSource":"official"},{"split":"unlicensed","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":141,"tasks":141,"splitTasks":141,"passes":45,"passRate":0.3191489361702128,"avgScore":0.5780645318965949,"totalDurationS":240790.42300000013,"totalInputTokens":1897081797,"totalOutputTokens":10619066,"totalCostUsd":382.88,"costSource":"official"},{"split":"unlicensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":141,"tasks":141,"splitTasks":141,"passes":43,"passRate":0.3049645390070922,"avgScore":0.5687211245398,"totalDurationS":170424.23500000002,"totalInputTokens":449345784,"totalOutputTokens":1514474,"totalCostUsd":601.41,"costSource":"official"},{"split":"unlicensed","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":141,"tasks":141,"splitTasks":141,"passes":45,"passRate":0.3191489361702128,"avgScore":0.5644732960303419,"totalDurationS":197574.713,"totalInputTokens":224650685,"totalOutputTokens":1456309,"totalCostUsd":362.29,"costSource":"official"},{"split":"unlicensed","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":141,"tasks":141,"splitTasks":141,"passes":44,"passRate":0.3120567375886525,"avgScore":0.559863564039273,"totalDurationS":349828.7960000001,"totalInputTokens":1061124629,"totalOutputTokens":5717720,"totalCostUsd":996.02,"costSource":"official"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":280,"tasks":141,"splitTasks":141,"passes":92,"passRate":0.3262411347517731,"avgScore":0.5595483966613978,"totalDurationS":291953.19649999996,"totalInputTokens":652364022.1666666,"totalOutputTokens":3478380.3333333335,"totalCostUsd":656.72,"costSource":"db+list"},{"split":"unlicensed","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":139,"tasks":139,"splitTasks":141,"passes":47,"passRate":0.3333333333333333,"avgScore":0.5546746675414325,"totalDurationS":466554.42300000007,"totalInputTokens":1972181022,"totalOutputTokens":13524667,"totalCostUsd":1946.38,"costSource":"official"},{"split":"unlicensed","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":138,"tasks":138,"splitTasks":141,"passes":41,"passRate":0.2907801418439716,"avgScore":0.5526026381504506,"totalDurationS":622739.765,"totalInputTokens":977228809,"totalOutputTokens":10754816,"totalCostUsd":406.16,"costSource":"db"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":278,"tasks":141,"splitTasks":141,"passes":91,"passRate":0.32978723404255317,"avgScore":0.5491172987872457,"totalDurationS":282712.47,"totalInputTokens":543170921.5,"totalOutputTokens":2693839,"totalCostUsd":525.89,"costSource":"db+list"},{"split":"unlicensed","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":140,"tasks":140,"splitTasks":141,"passes":42,"passRate":0.2978723404255319,"avgScore":0.5480545146373516,"totalDurationS":361649.22099999984,"totalInputTokens":692193035,"totalOutputTokens":3791370,"totalCostUsd":703.67,"costSource":"official"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":284,"tasks":141,"splitTasks":141,"passes":89,"passRate":0.3191489361702128,"avgScore":0.5473632833709104,"totalDurationS":311864.54466666665,"totalInputTokens":921100178.5,"totalOutputTokens":4976045.666666667,"totalCostUsd":903.28,"costSource":"db+list"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":280,"tasks":141,"splitTasks":141,"passes":87,"passRate":0.317966903073286,"avgScore":0.5430423343738866,"totalDurationS":273534.44200000004,"totalInputTokens":447187737.1666667,"totalOutputTokens":2005900.5,"totalCostUsd":424.24,"costSource":"db+list"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":141,"tasks":141,"splitTasks":141,"passes":44,"passRate":0.3120567375886525,"avgScore":0.5331379784041669,"totalDurationS":199793,"totalInputTokens":2398634685,"totalOutputTokens":6446026,"totalCostUsd":371.53,"costSource":"list"},{"split":"unlicensed","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":138,"tasks":138,"splitTasks":141,"passes":42,"passRate":0.2978723404255319,"avgScore":0.5303482128962862,"totalDurationS":570535.643,"totalInputTokens":941842570,"totalOutputTokens":6412623,"totalCostUsd":439.62,"costSource":"db"},{"split":"unlicensed","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":138,"tasks":138,"splitTasks":141,"passes":40,"passRate":0.28368794326241137,"avgScore":0.5269304388437668,"totalDurationS":637061.2620000002,"totalInputTokens":881625868,"totalOutputTokens":6896011,"totalCostUsd":432.22,"costSource":"db"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":277,"tasks":141,"splitTasks":141,"passes":81,"passRate":0.29432624113475175,"avgScore":0.5252918479026842,"totalDurationS":335753,"totalInputTokens":1147950590,"totalOutputTokens":5390942,"totalCostUsd":499.67,"costSource":"list"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":141,"tasks":141,"splitTasks":141,"passes":46,"passRate":0.3262411347517731,"avgScore":0.5206445104262789,"totalDurationS":189252,"totalInputTokens":1305756331,"totalOutputTokens":3877107,"totalCostUsd":212.65,"costSource":"list"},{"split":"unlicensed","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":140,"tasks":140,"splitTasks":141,"passes":39,"passRate":0.2765957446808511,"avgScore":0.5173999042242261,"totalDurationS":270855.705,"totalInputTokens":468237455,"totalOutputTokens":4689597,"totalCostUsd":235,"costSource":"db"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":277,"tasks":141,"splitTasks":141,"passes":82,"passRate":0.2978723404255319,"avgScore":0.5077329832154835,"totalDurationS":260404,"totalInputTokens":720897948,"totalOutputTokens":3526337,"totalCostUsd":331.24,"costSource":"list"},{"split":"unlicensed","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":140,"tasks":140,"splitTasks":141,"passes":38,"passRate":0.2695035460992908,"avgScore":0.5020995075154241,"totalDurationS":196439,"totalInputTokens":1779144434,"totalOutputTokens":9163045,"totalCostUsd":3187.09,"costSource":"official"},{"split":"unlicensed","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":278,"tasks":141,"splitTasks":141,"passes":80,"passRate":0.2872340425531915,"avgScore":0.49867589404218615,"totalDurationS":287393.5,"totalInputTokens":481345798.5,"totalOutputTokens":5745106.5,"totalCostUsd":522.76,"costSource":"db"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":276,"tasks":140,"splitTasks":141,"passes":77,"passRate":0.2801418439716312,"avgScore":0.48609115476187026,"totalDurationS":303490.11950000003,"totalInputTokens":480691367,"totalOutputTokens":2592990,"totalCostUsd":233.48,"costSource":"db+list"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":141,"tasks":141,"splitTasks":141,"passes":37,"passRate":0.2624113475177305,"avgScore":0.4789918638067592,"totalDurationS":142348,"totalInputTokens":643244149,"totalOutputTokens":2416086,"totalCostUsd":116.46,"costSource":"list"},{"split":"unlicensed","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":138,"tasks":138,"splitTasks":141,"passes":34,"passRate":0.24113475177304963,"avgScore":0.47658737865887824,"totalDurationS":117204.74566453496,"totalInputTokens":292991974,"totalOutputTokens":2165400,"totalCostUsd":275.26,"costSource":"db"},{"split":"unlicensed","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":139,"tasks":139,"splitTasks":141,"passes":41,"passRate":0.2907801418439716,"avgScore":0.4694146393591237,"totalDurationS":543814,"totalInputTokens":1465162311,"totalOutputTokens":20372367,"totalCostUsd":3696.61,"costSource":"published+task-ratio"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":278,"tasks":140,"splitTasks":141,"passes":72,"passRate":0.2541371158392435,"avgScore":0.4681048909575152,"totalDurationS":242446.52566666668,"totalInputTokens":230074698.16666666,"totalOutputTokens":1175061.3333333333,"totalCostUsd":223.43,"costSource":"db+list"},{"split":"unlicensed","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":412,"tasks":141,"splitTasks":141,"passes":109,"passRate":0.26122931442080377,"avgScore":0.46476081556733406,"totalDurationS":226290.44892996037,"totalInputTokens":417893865.5,"totalOutputTokens":3171073.8333333335,"totalCostUsd":339.05,"costSource":"db+list"},{"split":"unlicensed","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":130,"tasks":130,"splitTasks":141,"passes":32,"passRate":0.22695035460992907,"avgScore":0.44713736097477313,"totalDurationS":209777.7502665911,"totalInputTokens":317070704,"totalOutputTokens":3915017,"totalCostUsd":1564.2,"costSource":"official+adj"},{"split":"unlicensed","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":138,"tasks":138,"splitTasks":141,"passes":31,"passRate":0.2198581560283688,"avgScore":0.4459353752236476,"totalDurationS":873344.9099999998,"totalInputTokens":2489228093,"totalOutputTokens":14174887,"totalCostUsd":null,"costSource":null},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":276,"tasks":141,"splitTasks":141,"passes":69,"passRate":0.24468085106382978,"avgScore":0.4438320139384285,"totalDurationS":284946.718,"totalInputTokens":213612416.5,"totalOutputTokens":1450871,"totalCostUsd":111.31,"costSource":"db+list"},{"split":"unlicensed","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":131,"tasks":131,"splitTasks":141,"passes":33,"passRate":0.23404255319148937,"avgScore":0.44245775446794344,"totalDurationS":273966.4079745095,"totalInputTokens":403857647,"totalOutputTokens":3083904,"totalCostUsd":394.14,"costSource":"db"},{"split":"unlicensed","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":140,"tasks":140,"splitTasks":141,"passes":34,"passRate":0.24113475177304963,"avgScore":0.44189296504626746,"totalDurationS":416112,"totalInputTokens":1134598082,"totalOutputTokens":15341352,"totalCostUsd":2611.28,"costSource":"published+task-ratio"},{"split":"unlicensed","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":146,"tasks":138,"splitTasks":141,"passes":35,"passRate":0.24113475177304963,"avgScore":0.43941419463910386,"totalDurationS":323705.5,"totalInputTokens":745520634.5,"totalOutputTokens":8906113.5,"totalCostUsd":1828.62,"costSource":"official"},{"split":"unlicensed","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":135,"tasks":135,"splitTasks":141,"passes":34,"passRate":0.24113475177304963,"avgScore":0.4300608344770858,"totalDurationS":267844,"totalInputTokens":1571377795,"totalOutputTokens":5621171,"totalCostUsd":1508.33,"costSource":"published+task-ratio"},{"split":"unlicensed","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":136,"tasks":136,"splitTasks":141,"passes":31,"passRate":0.2198581560283688,"avgScore":0.4293016937371446,"totalDurationS":346433,"totalInputTokens":1263713696,"totalOutputTokens":7358995,"totalCostUsd":1057.31,"costSource":"db"},{"split":"unlicensed","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":136,"tasks":133,"splitTasks":141,"passes":33,"passRate":0.23049645390070922,"avgScore":0.42851304932922624,"totalDurationS":169469.4067363392,"totalInputTokens":128616018,"totalOutputTokens":1601327,"totalCostUsd":157.35,"costSource":"list"},{"split":"unlicensed","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":137,"tasks":134,"splitTasks":141,"passes":29,"passRate":0.19858156028368795,"avgScore":0.42800438644840083,"totalDurationS":468168.5,"totalInputTokens":1681873223.5,"totalOutputTokens":7582602,"totalCostUsd":867.99,"costSource":"db"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":278,"tasks":141,"splitTasks":141,"passes":60,"passRate":0.2198581560283688,"avgScore":0.42499288919011063,"totalDurationS":250208.747,"totalInputTokens":153532999,"totalOutputTokens":1050240.5,"totalCostUsd":79.42,"costSource":"db+list"},{"split":"unlicensed","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":134,"tasks":134,"splitTasks":141,"passes":31,"passRate":0.2198581560283688,"avgScore":0.42078661059033406,"totalDurationS":267485,"totalInputTokens":286472308,"totalOutputTokens":2720281,"totalCostUsd":150.04,"costSource":"db+list"},{"split":"unlicensed","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":138,"tasks":138,"splitTasks":141,"passes":27,"passRate":0.19148936170212766,"avgScore":0.4197333412241174,"totalDurationS":252612.16767463155,"totalInputTokens":1021079941,"totalOutputTokens":5088971,"totalCostUsd":923.69,"costSource":"official"},{"split":"unlicensed","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":134,"tasks":132,"splitTasks":141,"passes":30,"passRate":0.2127659574468085,"avgScore":0.4136390008783094,"totalDurationS":207594.6145255206,"totalInputTokens":214695571,"totalOutputTokens":2091602,"totalCostUsd":224.97,"costSource":"list"},{"split":"unlicensed","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":138,"tasks":138,"splitTasks":141,"passes":28,"passRate":0.19858156028368795,"avgScore":0.4114434329247684,"totalDurationS":179609,"totalInputTokens":235196044,"totalOutputTokens":2640977,"totalCostUsd":291.95,"costSource":"db"},{"split":"unlicensed","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":136,"tasks":136,"splitTasks":141,"passes":25,"passRate":0.1773049645390071,"avgScore":0.4067685680771121,"totalDurationS":466272,"totalInputTokens":307300337,"totalOutputTokens":3412910,"totalCostUsd":1328.51,"costSource":"official+adj"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":141,"tasks":141,"splitTasks":141,"passes":26,"passRate":0.18439716312056736,"avgScore":0.40056329147969094,"totalDurationS":140221,"totalInputTokens":223199374,"totalOutputTokens":996976,"totalCostUsd":44.72,"costSource":"list"},{"split":"unlicensed","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":172,"tasks":135,"splitTasks":141,"passes":40,"passRate":0.22104018912529552,"avgScore":0.39912759744833903,"totalDurationS":377603.43897103076,"totalInputTokens":418635161.1666667,"totalOutputTokens":6779006.166666667,"totalCostUsd":241.72,"costSource":"db"},{"split":"unlicensed","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":141,"tasks":141,"splitTasks":141,"passes":26,"passRate":0.18439716312056736,"avgScore":0.3828945809408762,"totalDurationS":108014,"totalInputTokens":96188305,"totalOutputTokens":1176916,"totalCostUsd":127.9,"costSource":"db"},{"split":"unlicensed","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":137,"tasks":136,"splitTasks":141,"passes":24,"passRate":0.1702127659574468,"avgScore":0.3745618668551661,"totalDurationS":403839.59668815427,"totalInputTokens":722150808,"totalOutputTokens":3808451.5,"totalCostUsd":1495.3,"costSource":"official+adj"},{"split":"unlicensed","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":130,"tasks":130,"splitTasks":141,"passes":21,"passRate":0.14893617021276595,"avgScore":0.3722051359473687,"totalDurationS":141696.4445367267,"totalInputTokens":380178747,"totalOutputTokens":3444699,"totalCostUsd":1558.83,"costSource":"official+adj"},{"split":"unlicensed","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":135,"tasks":135,"splitTasks":141,"passes":25,"passRate":0.1773049645390071,"avgScore":0.3480542170776246,"totalDurationS":317055,"totalInputTokens":1159533595,"totalOutputTokens":3389319,"totalCostUsd":1942.97,"costSource":"db+list+adj"},{"split":"unlicensed","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":135,"tasks":135,"splitTasks":141,"passes":18,"passRate":0.1276595744680851,"avgScore":0.33691021666783877,"totalDurationS":312987,"totalInputTokens":1245322848,"totalOutputTokens":17017497,"totalCostUsd":603.35,"costSource":"db+list"},{"split":"unlicensed","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":101,"tasks":95,"splitTasks":141,"passes":22,"passRate":0.1453900709219858,"avgScore":0.33663835749551463,"totalDurationS":99274.81146285753,"totalInputTokens":344833331.5,"totalOutputTokens":2642831,"totalCostUsd":1325.06,"costSource":"official+adj"},{"split":"unlicensed","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":140,"tasks":140,"splitTasks":141,"passes":19,"passRate":0.1347517730496454,"avgScore":0.3346469768128772,"totalDurationS":630410,"totalInputTokens":1601437068,"totalOutputTokens":20409603,"totalCostUsd":439.63,"costSource":"db"},{"split":"unlicensed","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":141,"tasks":141,"splitTasks":141,"passes":18,"passRate":0.1276595744680851,"avgScore":0.3280611890351934,"totalDurationS":77880,"totalInputTokens":102309910,"totalOutputTokens":562218,"totalCostUsd":22.46,"costSource":"list"},{"split":"unlicensed","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":142,"tasks":134,"splitTasks":141,"passes":22,"passRate":0.1524822695035461,"avgScore":0.31130806689351526,"totalDurationS":449865.6185256547,"totalInputTokens":2913806051,"totalOutputTokens":3449466,"totalCostUsd":2624.2,"costSource":"db+adj"},{"split":"unlicensed","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":137,"tasks":137,"splitTasks":141,"passes":18,"passRate":0.1276595744680851,"avgScore":0.30617200210871603,"totalDurationS":156584.72501084246,"totalInputTokens":771282392,"totalOutputTokens":1721086,"totalCostUsd":247.31,"costSource":"db"},{"split":"unlicensed","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":267,"tasks":139,"splitTasks":141,"passes":39,"passRate":0.13356973995271867,"avgScore":0.2968980544087109,"totalDurationS":429886.8668230823,"totalInputTokens":484585706.8333333,"totalOutputTokens":4577953.166666667,"totalCostUsd":251.83,"costSource":"db"},{"split":"unlicensed","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":251,"tasks":134,"splitTasks":141,"passes":35,"passRate":0.12411347517730496,"avgScore":0.2966678841504093,"totalDurationS":527433.7247366491,"totalInputTokens":592066637.8333334,"totalOutputTokens":5130397,"totalCostUsd":348.97,"costSource":"db+list"},{"split":"unlicensed","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":262,"tasks":139,"splitTasks":141,"passes":25,"passRate":0.09219858156028368,"avgScore":0.26021994074929344,"totalDurationS":438548.9462786893,"totalInputTokens":618181138.6666666,"totalOutputTokens":6451781.833333333,"totalCostUsd":213.49,"costSource":"db"},{"split":"unlicensed","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":251,"tasks":139,"splitTasks":141,"passes":25,"passRate":0.09219858156028368,"avgScore":0.2500876678582964,"totalDurationS":356215.3619929354,"totalInputTokens":342350334.1666667,"totalOutputTokens":3820122.8333333335,"totalCostUsd":38.49,"costSource":"db+list"},{"split":"unlicensed","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":234,"tasks":137,"splitTasks":141,"passes":25,"passRate":0.09929078014184398,"avgScore":0.2292968817611259,"totalDurationS":563409.5122970284,"totalInputTokens":293251082.5,"totalOutputTokens":5966124,"totalCostUsd":121.61,"costSource":"db+list"},{"split":"unlicensed","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":142,"tasks":135,"splitTasks":141,"passes":11,"passRate":0.07801418439716312,"avgScore":0.22826886829139284,"totalDurationS":155064.3737437582,"totalInputTokens":223145635.66666666,"totalOutputTokens":2267515.6666666665,"totalCostUsd":284.6,"costSource":"list"},{"split":"unlicensed","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":252,"tasks":138,"splitTasks":141,"passes":13,"passRate":0.04609929078014184,"avgScore":0.16924662466040963,"totalDurationS":252321.35201545496,"totalInputTokens":160417983.5,"totalOutputTokens":2603273,"totalCostUsd":75.26,"costSource":"db+list"},{"split":"unlicensed","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":216,"tasks":139,"splitTasks":141,"passes":14,"passRate":0.06382978723404255,"avgScore":0.1492606367247545,"totalDurationS":442594.7348369967,"totalInputTokens":274979228.6666667,"totalOutputTokens":3748463.1666666665,"totalCostUsd":25.31,"costSource":"db+list"},{"split":"unlicensed","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":137,"tasks":135,"splitTasks":141,"passes":11,"passRate":0.07801418439716312,"avgScore":0.13781504500323477,"totalDurationS":121711.8690922095,"totalInputTokens":168779753.5,"totalOutputTokens":2988511.5,"totalCostUsd":117.05,"costSource":"db"},{"split":"unlicensed","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":136,"tasks":134,"splitTasks":141,"passes":7,"passRate":0.04964539007092199,"avgScore":0.1351355595285674,"totalDurationS":65573.95362966345,"totalInputTokens":55532219.5,"totalOutputTokens":512410,"totalCostUsd":174.28,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":50,"tasks":50,"splitTasks":50,"passes":16,"passRate":0.32,"avgScore":0.5163008264025186,"totalDurationS":129966.02100000001,"totalInputTokens":84348529,"totalOutputTokens":1547463,"totalCostUsd":199.91,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":50,"tasks":50,"splitTasks":50,"passes":14,"passRate":0.28,"avgScore":0.5025224516648259,"totalDurationS":54728.17599999999,"totalInputTokens":446649032,"totalOutputTokens":3312998,"totalCostUsd":95.74,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":50,"tasks":50,"splitTasks":50,"passes":15,"passRate":0.3,"avgScore":0.495340772211687,"totalDurationS":58570.56399999999,"totalInputTokens":60983837,"totalOutputTokens":628106,"totalCostUsd":115.84,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":50,"tasks":50,"splitTasks":50,"passes":15,"passRate":0.3,"avgScore":0.4880787466528,"totalDurationS":108821.80299999999,"totalInputTokens":413781777,"totalOutputTokens":2994122,"totalCostUsd":396.47,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":50,"tasks":50,"splitTasks":50,"passes":13,"passRate":0.26,"avgScore":0.4859165712897115,"totalDurationS":89522.56300000004,"totalInputTokens":80229194,"totalOutputTokens":1070219,"totalCostUsd":166.35,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":49,"tasks":49,"splitTasks":50,"passes":14,"passRate":0.28,"avgScore":0.48133859388693956,"totalDurationS":160811.89200000002,"totalInputTokens":283369221,"totalOutputTokens":2184498,"totalCostUsd":138.27,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":50,"tasks":50,"splitTasks":50,"passes":15,"passRate":0.3,"avgScore":0.4799408516017688,"totalDurationS":58398.426000000014,"totalInputTokens":543851453,"totalOutputTokens":3376306,"totalCostUsd":114.53,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":50,"tasks":50,"splitTasks":50,"passes":13,"passRate":0.26,"avgScore":0.4699132742819965,"totalDurationS":91950.784,"totalInputTokens":76747998,"totalOutputTokens":912519,"totalCostUsd":152.27,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":48,"tasks":48,"splitTasks":50,"passes":12,"passRate":0.24,"avgScore":0.46727232361384374,"totalDurationS":161452.09199999998,"totalInputTokens":298336188,"totalOutputTokens":3103340,"totalCostUsd":120.6,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":97,"tasks":50,"splitTasks":50,"passes":30,"passRate":0.3,"avgScore":0.4631298337170319,"totalDurationS":77278.69649999999,"totalInputTokens":177738481.5,"totalOutputTokens":1150322.5,"totalCostUsd":204.09,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":99,"tasks":50,"splitTasks":50,"passes":26,"passRate":0.26,"avgScore":0.4512691704888627,"totalDurationS":94791.5,"totalInputTokens":269660670.5,"totalOutputTokens":1641035.5,"totalCostUsd":129.2,"costSource":"list"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":50,"tasks":50,"splitTasks":50,"passes":14,"passRate":0.28,"avgScore":0.4491114731176944,"totalDurationS":79411.84799999998,"totalInputTokens":165286100,"totalOutputTokens":1082789,"totalCostUsd":175.07,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":50,"tasks":50,"splitTasks":50,"passes":12,"passRate":0.24,"avgScore":0.44886758614268696,"totalDurationS":74915.91,"totalInputTokens":296076569,"totalOutputTokens":1941555,"totalCostUsd":262.9,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":50,"tasks":50,"splitTasks":50,"passes":12,"passRate":0.24,"avgScore":0.44809817984234634,"totalDurationS":125632.35800000001,"totalInputTokens":555994091,"totalOutputTokens":4315091,"totalCostUsd":538.36,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":99,"tasks":50,"splitTasks":50,"passes":27,"passRate":0.28,"avgScore":0.44650364852254953,"totalDurationS":72734.942,"totalInputTokens":98748623.5,"totalOutputTokens":639137,"totalCostUsd":113.39,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":50,"tasks":50,"splitTasks":50,"passes":15,"passRate":0.3,"avgScore":0.4433841810461951,"totalDurationS":47507,"totalInputTokens":585468127,"totalOutputTokens":2068701,"totalCostUsd":95.07,"costSource":"list"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":100,"tasks":50,"splitTasks":50,"passes":25,"passRate":0.26,"avgScore":0.44076492497958797,"totalDurationS":74690.378,"totalInputTokens":217198822,"totalOutputTokens":1560829.1666666667,"totalCostUsd":239.3,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":50,"tasks":50,"splitTasks":50,"passes":13,"passRate":0.26,"avgScore":0.44075007111357833,"totalDurationS":142651.07799999998,"totalInputTokens":641676672,"totalOutputTokens":4729835,"totalCostUsd":619.5,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":50,"tasks":50,"splitTasks":50,"passes":11,"passRate":0.22,"avgScore":0.4381661093894904,"totalDurationS":68112.29,"totalInputTokens":44797996,"totalOutputTokens":400695,"totalCostUsd":83.2,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":50,"tasks":50,"splitTasks":50,"passes":14,"passRate":0.28,"avgScore":0.4356378222921257,"totalDurationS":26559,"totalInputTokens":174023797,"totalOutputTokens":768309,"totalCostUsd":33.54,"costSource":"list"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":49,"tasks":49,"splitTasks":50,"passes":11,"passRate":0.22,"avgScore":0.4351458390524464,"totalDurationS":182599.69500000004,"totalInputTokens":254930145,"totalOutputTokens":2186567,"totalCostUsd":125.25,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":99,"tasks":50,"splitTasks":50,"passes":28,"passRate":0.28,"avgScore":0.433638270435078,"totalDurationS":81367.47,"totalInputTokens":124762948,"totalOutputTokens":846635.5,"totalCostUsd":138.39,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":50,"tasks":50,"splitTasks":50,"passes":11,"passRate":0.22,"avgScore":0.43039726926162564,"totalDurationS":290651.849,"totalInputTokens":1068561142,"totalOutputTokens":5121884,"totalCostUsd":null,"costSource":null},{"split":"unlicensed/full-spectrum","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":50,"tasks":50,"splitTasks":50,"passes":11,"passRate":0.22,"avgScore":0.4247048184505826,"totalDurationS":78269.59600000002,"totalInputTokens":133916121,"totalOutputTokens":1752563,"totalCostUsd":67.58,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":50,"tasks":50,"splitTasks":50,"passes":12,"passRate":0.24,"avgScore":0.41885525446026206,"totalDurationS":174938,"totalInputTokens":396448337,"totalOutputTokens":7507408,"totalCostUsd":1203.45,"costSource":"published+task-ratio"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":50,"tasks":50,"splitTasks":50,"passes":14,"passRate":0.28,"avgScore":0.4177055625187485,"totalDurationS":51596,"totalInputTokens":299155581,"totalOutputTokens":1250311,"totalCostUsd":53.18,"costSource":"list"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":50,"tasks":50,"splitTasks":50,"passes":10,"passRate":0.2,"avgScore":0.4154396674522125,"totalDurationS":44770.99600000001,"totalInputTokens":61290567,"totalOutputTokens":433045,"totalCostUsd":103.95,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":100,"tasks":50,"splitTasks":50,"passes":25,"passRate":0.25,"avgScore":0.4148733134041199,"totalDurationS":73476,"totalInputTokens":177458632.5,"totalOutputTokens":1109713,"totalCostUsd":91.53,"costSource":"list"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":50,"tasks":50,"splitTasks":50,"passes":12,"passRate":0.24,"avgScore":0.4044353533333333,"totalDurationS":66288,"totalInputTokens":619603149,"totalOutputTokens":3129503,"totalCostUsd":1208.7,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":99,"tasks":50,"splitTasks":50,"passes":21,"passRate":0.22,"avgScore":0.39558362254691226,"totalDurationS":93679.6195,"totalInputTokens":131879860,"totalOutputTokens":836993,"totalCostUsd":67.99,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":49,"tasks":49,"splitTasks":50,"passes":11,"passRate":0.22,"avgScore":0.39352714009093803,"totalDurationS":24984.74481033199,"totalInputTokens":37425146,"totalOutputTokens":628019,"totalCostUsd":53.27,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":49,"tasks":49,"splitTasks":50,"passes":10,"passRate":0.2,"avgScore":0.3933536738539414,"totalDurationS":76526,"totalInputTokens":544268438,"totalOutputTokens":1875055,"totalCostUsd":516.84,"costSource":"published+task-ratio"},{"split":"unlicensed/full-spectrum","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":48,"tasks":48,"splitTasks":50,"passes":11,"passRate":0.22,"avgScore":0.39292900253171503,"totalDurationS":40744.41926420876,"totalInputTokens":128052474,"totalOutputTokens":1427847,"totalCostUsd":580.62,"costSource":"official+adj"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":98,"tasks":50,"splitTasks":50,"passes":20,"passRate":0.2,"avgScore":0.39285408160616503,"totalDurationS":65719.859,"totalInputTokens":59225023.5,"totalOutputTokens":389348.5,"totalCostUsd":61.9,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":49,"tasks":49,"splitTasks":50,"passes":11,"passRate":0.22,"avgScore":0.3902936019318159,"totalDurationS":117678,"totalInputTokens":497249334,"totalOutputTokens":2871641,"totalCostUsd":264.89,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":98,"tasks":50,"splitTasks":50,"passes":22,"passRate":0.22,"avgScore":0.38708429229256636,"totalDurationS":74170.5,"totalInputTokens":100347290.5,"totalOutputTokens":1853010,"totalCostUsd":135.4,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":50,"tasks":50,"splitTasks":50,"passes":10,"passRate":0.2,"avgScore":0.3793836589504913,"totalDurationS":115789,"totalInputTokens":255949496,"totalOutputTokens":5279930,"totalCostUsd":777.77,"costSource":"published+task-ratio"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":52,"tasks":50,"splitTasks":50,"passes":12,"passRate":0.23,"avgScore":0.37312465627900904,"totalDurationS":86760,"totalInputTokens":301449420,"totalOutputTokens":3311822.5,"totalCostUsd":555.24,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":146,"tasks":50,"splitTasks":50,"passes":34,"passRate":0.22666666666666668,"avgScore":0.3693544973841823,"totalDurationS":46836.10881495468,"totalInputTokens":91586748.5,"totalOutputTokens":987275.5,"totalCostUsd":90.3,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":49,"tasks":49,"splitTasks":50,"passes":9,"passRate":0.18,"avgScore":0.36831414074161306,"totalDurationS":105972,"totalInputTokens":323665898,"totalOutputTokens":2488434,"totalCostUsd":375.15,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":49,"tasks":49,"splitTasks":50,"passes":9,"passRate":0.18,"avgScore":0.36513474394967993,"totalDurationS":47608.04235754142,"totalInputTokens":222692155,"totalOutputTokens":1493759,"totalCostUsd":201.89,"costSource":"official"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":100,"tasks":50,"splitTasks":50,"passes":19,"passRate":0.19,"avgScore":0.36165443790798124,"totalDurationS":67713.747,"totalInputTokens":43552329,"totalOutputTokens":365133,"totalCostUsd":24.84,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":47,"tasks":47,"splitTasks":50,"passes":9,"passRate":0.18,"avgScore":0.3503439333349274,"totalDurationS":53747.939585612694,"totalInputTokens":49922490,"totalOutputTokens":723508,"totalCostUsd":61.39,"costSource":"list"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":66,"tasks":49,"splitTasks":50,"passes":12,"passRate":0.19333333333333333,"avgScore":0.3485832185191737,"totalDurationS":145051.03629214008,"totalInputTokens":174969360.16666666,"totalOutputTokens":2447842.6666666665,"totalCostUsd":92.85,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":50,"tasks":50,"splitTasks":50,"passes":9,"passRate":0.18,"avgScore":0.34037980623548364,"totalDurationS":28603,"totalInputTokens":21829853,"totalOutputTokens":377771,"totalCostUsd":35.01,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":100,"tasks":50,"splitTasks":50,"passes":18,"passRate":0.18,"avgScore":0.3390348819796931,"totalDurationS":88605.218,"totalInputTokens":62817795.5,"totalOutputTokens":496519.5,"totalCostUsd":34.63,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":48,"tasks":48,"splitTasks":50,"passes":10,"passRate":0.2,"avgScore":0.3361494333333333,"totalDurationS":42562.361035950235,"totalInputTokens":31812048,"totalOutputTokens":496590,"totalCostUsd":44.52,"costSource":"list"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":47,"tasks":47,"splitTasks":50,"passes":9,"passRate":0.18,"avgScore":0.3266237832837682,"totalDurationS":65810.74335963264,"totalInputTokens":68495850,"totalOutputTokens":915984,"totalCostUsd":79.18,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":49,"tasks":49,"splitTasks":50,"passes":8,"passRate":0.16,"avgScore":0.31952009526446135,"totalDurationS":55456,"totalInputTokens":58511596,"totalOutputTokens":965128,"totalCostUsd":82.36,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":48,"tasks":48,"splitTasks":50,"passes":9,"passRate":0.18,"avgScore":0.31867703057507313,"totalDurationS":81703,"totalInputTokens":85627286,"totalOutputTokens":928266,"totalCostUsd":45.13,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":49,"tasks":49,"splitTasks":50,"passes":6,"passRate":0.12,"avgScore":0.3038085248805724,"totalDurationS":93824,"totalInputTokens":501226643,"totalOutputTokens":6740794,"totalCostUsd":244.25,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":50,"tasks":50,"splitTasks":50,"passes":6,"passRate":0.12,"avgScore":0.2984717724109289,"totalDurationS":159935,"totalInputTokens":97287341,"totalOutputTokens":1049930,"totalCostUsd":415.82,"costSource":"official+adj"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":50,"tasks":50,"splitTasks":50,"passes":6,"passRate":0.12,"avgScore":0.2963635563049718,"totalDurationS":27012,"totalInputTokens":51495533,"totalOutputTokens":311061,"totalCostUsd":11.82,"costSource":"list"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":48,"tasks":48,"splitTasks":50,"passes":5,"passRate":0.1,"avgScore":0.2777319707686421,"totalDurationS":81810.31944376754,"totalInputTokens":126991014,"totalOutputTokens":1028842,"totalCostUsd":301.67,"costSource":"official+adj"},{"split":"unlicensed/full-spectrum","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":46,"tasks":46,"splitTasks":50,"passes":6,"passRate":0.12,"avgScore":0.27546770029157375,"totalDurationS":34153.082216965966,"totalInputTokens":138650190,"totalOutputTokens":1350638,"totalCostUsd":559.29,"costSource":"official+adj"},{"split":"unlicensed/full-spectrum","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":50,"tasks":50,"splitTasks":50,"passes":7,"passRate":0.14,"avgScore":0.2594230155582648,"totalDurationS":149176,"totalInputTokens":569736882,"totalOutputTokens":7679404,"totalCostUsd":171.28,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":49,"tasks":49,"splitTasks":50,"passes":6,"passRate":0.12,"avgScore":0.25745041514387507,"totalDurationS":78150,"totalInputTokens":429544179,"totalOutputTokens":1577347,"totalCostUsd":888.72,"costSource":"db+list+adj"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":91,"tasks":49,"splitTasks":50,"passes":11,"passRate":0.11,"avgScore":0.24938953000000005,"totalDurationS":105415.88512140546,"totalInputTokens":99504576.5,"totalOutputTokens":1380513.8333333333,"totalCostUsd":57.34,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":89,"tasks":49,"splitTasks":50,"passes":8,"passRate":0.09,"avgScore":0.24758475908000527,"totalDurationS":127467.2211974289,"totalInputTokens":228166672.83333334,"totalOutputTokens":2579788.3333333335,"totalCostUsd":79.18,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":50,"tasks":50,"splitTasks":50,"passes":3,"passRate":0.06,"avgScore":0.24564591975351033,"totalDurationS":15568,"totalInputTokens":28407280,"totalOutputTokens":188827,"totalCostUsd":6.8,"costSource":"list"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":82,"tasks":44,"splitTasks":50,"passes":10,"passRate":0.1,"avgScore":0.22985225925256939,"totalDurationS":161077.19640037167,"totalInputTokens":165805606,"totalOutputTokens":1715714.5,"totalCostUsd":100.65,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":51,"tasks":47,"splitTasks":50,"passes":5,"passRate":0.1,"avgScore":0.22743563333333333,"totalDurationS":183302.91810718234,"totalInputTokens":1373512411,"totalOutputTokens":1585963,"totalCostUsd":1191.3,"costSource":"db+adj"},{"split":"unlicensed/full-spectrum","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":49,"tasks":49,"splitTasks":50,"passes":4,"passRate":0.08,"avgScore":0.22512809050649008,"totalDurationS":40180.566417631,"totalInputTokens":301408364,"totalOutputTokens":615102,"totalCostUsd":93.03,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":90,"tasks":49,"splitTasks":50,"passes":9,"passRate":0.1,"avgScore":0.21744599999999994,"totalDurationS":99113.22360567635,"totalInputTokens":125903257.16666667,"totalOutputTokens":1210919.8333333333,"totalCostUsd":13.46,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":47,"tasks":45,"splitTasks":50,"passes":4,"passRate":0.08,"avgScore":0.19911717333333329,"totalDurationS":37048.293881934966,"totalInputTokens":73102727.66666667,"totalOutputTokens":884425.6666666666,"totalCostUsd":93.59,"costSource":"list"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":82,"tasks":49,"splitTasks":50,"passes":6,"passRate":0.07,"avgScore":0.18828448362311412,"totalDurationS":204363.24344928894,"totalInputTokens":92029776,"totalOutputTokens":2361976.5,"totalCostUsd":39.81,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":88,"tasks":49,"splitTasks":50,"passes":4,"passRate":0.04,"avgScore":0.14656085333333332,"totalDurationS":66785.42843375677,"totalInputTokens":45099322.5,"totalOutputTokens":908955,"totalCostUsd":21.32,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":47,"tasks":45,"splitTasks":50,"passes":3,"passRate":0.06,"avgScore":0.140505150751521,"totalDurationS":14270.642271389253,"totalInputTokens":20789954.5,"totalOutputTokens":177795,"totalCostUsd":65.04,"costSource":"db"},{"split":"unlicensed/full-spectrum","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":18,"tasks":18,"splitTasks":50,"passes":1,"passRate":0.02,"avgScore":0.09501958811261163,"totalDurationS":10051.606426970102,"totalInputTokens":36489552,"totalOutputTokens":423717,"totalCostUsd":150.16,"costSource":"official+adj"},{"split":"unlicensed/full-spectrum","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":79,"tasks":49,"splitTasks":50,"passes":2,"passRate":0.04,"avgScore":0.08225000000000002,"totalDurationS":127004.4180870185,"totalInputTokens":92955565.16666667,"totalOutputTokens":1210495.1666666667,"totalCostUsd":8.45,"costSource":"db+list"},{"split":"unlicensed/full-spectrum","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":47,"tasks":45,"splitTasks":50,"passes":2,"passRate":0.04,"avgScore":0.06738161075152099,"totalDurationS":16650.077705071075,"totalInputTokens":28237254.5,"totalOutputTokens":805350.5,"totalCostUsd":24,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":30,"tasks":30,"splitTasks":30,"passes":4,"passRate":0.13333333333333333,"avgScore":0.32028689872250954,"totalDurationS":100725.90599999999,"totalInputTokens":125268358,"totalOutputTokens":1036329,"totalCostUsd":206.65,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":30,"tasks":30,"splitTasks":30,"passes":4,"passRate":0.13333333333333333,"avgScore":0.3115585523428595,"totalDurationS":151427.11000000002,"totalInputTokens":128351834,"totalOutputTokens":1797549,"totalCostUsd":256,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":29,"tasks":29,"splitTasks":30,"passes":4,"passRate":0.13333333333333333,"avgScore":0.30405746719557086,"totalDurationS":191675.875,"totalInputTokens":333196615,"totalOutputTokens":1686022,"totalCostUsd":348.2,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":30,"tasks":30,"splitTasks":30,"passes":3,"passRate":0.1,"avgScore":0.3035459160773017,"totalDurationS":113111.78899999999,"totalInputTokens":150736709,"totalOutputTokens":1323566,"totalCostUsd":254.34,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":30,"tasks":30,"splitTasks":30,"passes":4,"passRate":0.13333333333333333,"avgScore":0.30077514934159777,"totalDurationS":106678.46600000001,"totalInputTokens":146431540,"totalOutputTokens":844317,"totalCostUsd":214.72,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":29,"tasks":29,"splitTasks":30,"passes":4,"passRate":0.13333333333333333,"avgScore":0.28130858943822107,"totalDurationS":260986.983,"totalInputTokens":394942645,"totalOutputTokens":3581950,"totalCostUsd":164.29,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":30,"tasks":30,"splitTasks":30,"passes":4,"passRate":0.13333333333333333,"avgScore":0.2781416236197514,"totalDurationS":89539.646,"totalInputTokens":99059092,"totalOutputTokens":566104,"totalCostUsd":147.88,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":30,"tasks":30,"splitTasks":30,"passes":4,"passRate":0.13333333333333333,"avgScore":0.2721051770453527,"totalDurationS":243374.543,"totalInputTokens":914195921,"totalOutputTokens":6367027,"totalCostUsd":879.08,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":30,"tasks":30,"splitTasks":30,"passes":3,"passRate":0.1,"avgScore":0.26864074866936366,"totalDurationS":129787.19099999999,"totalInputTokens":966771121,"totalOutputTokens":3735134,"totalCostUsd":182.23,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":30,"tasks":30,"splitTasks":30,"passes":3,"passRate":0.1,"avgScore":0.26720489668060127,"totalDurationS":181959.37399999998,"totalInputTokens":525538869,"totalOutputTokens":2381669,"totalCostUsd":482.35,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":29,"tasks":29,"splitTasks":30,"passes":3,"passRate":0.1,"avgScore":0.2599925642365976,"totalDurationS":177177.27,"totalInputTokens":542761748,"totalOutputTokens":3723362,"totalCostUsd":562.14,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":30,"tasks":30,"splitTasks":30,"passes":4,"passRate":0.13333333333333333,"avgScore":0.25482074597591664,"totalDurationS":115519.88900000001,"totalInputTokens":1108361014,"totalOutputTokens":4584281,"totalCostUsd":212.99,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":30,"tasks":30,"splitTasks":30,"passes":3,"passRate":0.1,"avgScore":0.2528695198601392,"totalDurationS":84764.094,"totalInputTokens":254462256,"totalOutputTokens":533209,"totalCostUsd":305.34,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":28,"tasks":28,"splitTasks":30,"passes":3,"passRate":0.1,"avgScore":0.23142431676345085,"totalDurationS":255720.027,"totalInputTokens":410514334,"totalOutputTokens":2347073,"totalCostUsd":186.26,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":28,"tasks":28,"splitTasks":30,"passes":5,"passRate":0.16666666666666666,"avgScore":0.22639176476300713,"totalDurationS":198267.68299999996,"totalInputTokens":681507929,"totalOutputTokens":4337723,"totalCostUsd":702.18,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":61,"tasks":30,"splitTasks":30,"passes":4,"passRate":0.06666666666666667,"avgScore":0.20737264567839306,"totalDurationS":97842,"totalInputTokens":297768333.3333333,"totalOutputTokens":1208400.8333333333,"totalCostUsd":259.53,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":29,"tasks":29,"splitTasks":30,"passes":4,"passRate":0.13333333333333333,"avgScore":0.2007545188144268,"totalDurationS":253347.01599999997,"totalInputTokens":444162978,"totalOutputTokens":2434975,"totalCostUsd":198.09,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":29,"tasks":29,"splitTasks":30,"passes":3,"passRate":0.1,"avgScore":0.1967489930133485,"totalDurationS":132480.78900000002,"totalInputTokens":118841427,"totalOutputTokens":1292528,"totalCostUsd":59.19,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":59,"tasks":30,"splitTasks":30,"passes":3,"passRate":0.06666666666666667,"avgScore":0.19652298994758152,"totalDurationS":89607,"totalInputTokens":273176548.5,"totalOutputTokens":948762,"totalCostUsd":227.28,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":59,"tasks":30,"splitTasks":30,"passes":2,"passRate":0.05,"avgScore":0.18922557053100295,"totalDurationS":84648,"totalInputTokens":231236782,"totalOutputTokens":657382,"totalCostUsd":183.03,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":61,"tasks":30,"splitTasks":30,"passes":2,"passRate":0.03333333333333333,"avgScore":0.16687270502343013,"totalDurationS":100360.83333333333,"totalInputTokens":417867333.6666667,"totalOutputTokens":1796854.5,"totalCostUsd":364.96,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":29,"tasks":29,"splitTasks":30,"passes":3,"passRate":0.1,"avgScore":0.16393594595273656,"totalDurationS":63512,"totalInputTokens":734827171,"totalOutputTokens":2889009,"totalCostUsd":1087.64,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":29,"tasks":29,"splitTasks":30,"passes":1,"passRate":0.03333333333333333,"avgScore":0.16051822822903797,"totalDurationS":225064,"totalInputTokens":858187522,"totalOutputTokens":6121545,"totalCostUsd":1425.24,"costSource":"published+task-ratio"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":30,"tasks":30,"splitTasks":30,"passes":1,"passRate":0.03333333333333333,"avgScore":0.1505198327191624,"totalDurationS":79440,"totalInputTokens":1321242146,"totalOutputTokens":2441114,"totalCostUsd":189.81,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":59,"tasks":30,"splitTasks":30,"passes":1,"passRate":0.016666666666666666,"avgScore":0.15026470889226193,"totalDurationS":114277.5,"totalInputTokens":262571368,"totalOutputTokens":1892772.5,"totalCostUsd":231.75,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":58,"tasks":30,"splitTasks":30,"passes":2,"passRate":0.03333333333333333,"avgScore":0.15022183083314491,"totalDurationS":115749.5,"totalInputTokens":627914170,"totalOutputTokens":2004620,"totalCostUsd":239.29,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":28,"tasks":28,"splitTasks":30,"passes":1,"passRate":0.03333333333333333,"avgScore":0.1459374165601684,"totalDurationS":41648.47447400001,"totalInputTokens":91673091,"totalOutputTokens":597458,"totalCostUsd":80.38,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":28,"tasks":28,"splitTasks":30,"passes":1,"passRate":0.03333333333333333,"avgScore":0.13893693343958233,"totalDurationS":324532.41500000004,"totalInputTokens":808120996,"totalOutputTokens":3483338,"totalCostUsd":null,"costSource":null},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":85,"tasks":30,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.1336927248629258,"totalDurationS":87267.92330068085,"totalInputTokens":169216522.5,"totalOutputTokens":987069.5,"totalCostUsd":135.97,"costSource":"db+list"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":27,"tasks":27,"splitTasks":30,"passes":1,"passRate":0.03333333333333333,"avgScore":0.12965036002828909,"totalDurationS":150498,"totalInputTokens":763499702,"totalOutputTokens":2426146,"totalCostUsd":617.92,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":22,"tasks":22,"splitTasks":30,"passes":1,"passRate":0.03333333333333333,"avgScore":0.12847049593392926,"totalDurationS":58179.24658737797,"totalInputTokens":92176971,"totalOutputTokens":1046938,"totalCostUsd":496.57,"costSource":"official+adj"},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":29,"tasks":29,"splitTasks":30,"passes":1,"passRate":0.03333333333333333,"avgScore":0.12697865037281922,"totalDurationS":81523,"totalInputTokens":101477070,"totalOutputTokens":750493,"totalCostUsd":110.16,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":28,"tasks":26,"splitTasks":30,"passes":1,"passRate":0.03333333333333333,"avgScore":0.12633812830701532,"totalDurationS":75297.65644168308,"totalInputTokens":71979435,"totalOutputTokens":506281,"totalCostUsd":65.27,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":58,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.12315914835731925,"totalDurationS":87469.83333333333,"totalInputTokens":102937640,"totalOutputTokens":356578.8333333333,"totalCostUsd":85.84,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":25,"tasks":25,"splitTasks":30,"passes":1,"passRate":0.03333333333333333,"avgScore":0.11836513333333333,"totalDurationS":21599.263863500804,"totalInputTokens":48704376,"totalOutputTokens":415252,"totalCostUsd":49.65,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":30,"tasks":30,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.11752938705842898,"totalDurationS":71143,"totalInputTokens":665277010,"totalOutputTokens":1151373,"totalCostUsd":94.89,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":26,"tasks":26,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.11091326666666665,"totalDurationS":118920,"totalInputTokens":115603663,"totalOutputTokens":860852,"totalCostUsd":59.95,"costSource":"db+list"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":56,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.10630694231146019,"totalDurationS":75359.5,"totalInputTokens":204857419.5,"totalOutputTokens":845060.5,"totalCostUsd":87.9,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":59,"tasks":30,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.10511247258063579,"totalDurationS":73434,"totalInputTokens":51763892.5,"totalOutputTokens":279262.5,"totalCostUsd":23.24,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":25,"tasks":25,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.10429084991739138,"totalDurationS":67603.12073842585,"totalInputTokens":119273828,"totalOutputTokens":841764,"totalCostUsd":107.24,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":28,"tasks":28,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.10303376953774213,"totalDurationS":56400.74217087712,"totalInputTokens":296584939,"totalOutputTokens":472813,"totalCostUsd":91.02,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":57,"tasks":30,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.10286059924850519,"totalDurationS":74813.5,"totalInputTokens":71099685.5,"totalOutputTokens":415960,"totalCostUsd":32.32,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":57,"tasks":30,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.10081890647001854,"totalDurationS":81127.5,"totalInputTokens":384973196,"totalOutputTokens":1243671,"totalCostUsd":151.35,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":30,"tasks":30,"splitTasks":30,"passes":1,"passRate":0.03333333333333333,"avgScore":0.09925073212365117,"totalDurationS":173011,"totalInputTokens":706933041,"totalOutputTokens":4977921,"totalCostUsd":1101.41,"costSource":"published+task-ratio"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":30,"tasks":30,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.09622840053229612,"totalDurationS":14261,"totalInputTokens":29419495,"totalOutputTokens":127636,"totalCostUsd":5.65,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":30,"tasks":30,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.09288872936875796,"totalDurationS":46146,"totalInputTokens":48327687,"totalOutputTokens":310243,"totalCostUsd":48.7,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":33,"tasks":27,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.09269565733477077,"totalDurationS":102235.1495168395,"totalInputTokens":169121874.16666666,"totalOutputTokens":2307577,"totalCostUsd":89.77,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":26,"tasks":25,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.09082621935752275,"totalDurationS":130045,"totalInputTokens":514960913.5,"totalOutputTokens":2127521.5,"totalCostUsd":270.72,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":29,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.08979562737969146,"totalDurationS":234890,"totalInputTokens":455884298,"totalOutputTokens":4778683,"totalCostUsd":84.7,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":26,"tasks":26,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.08768284482818715,"totalDurationS":57084.972001090646,"totalInputTokens":134441437,"totalOutputTokens":1284319,"totalCostUsd":576.53,"costSource":"official+adj"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":26,"tasks":26,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.0856096444480286,"totalDurationS":135036,"totalInputTokens":726419627,"totalOutputTokens":1662333,"totalCostUsd":580.14,"costSource":"published+task-ratio"},{"split":"unlicensed/last-exam","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":17,"tasks":17,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.08531923866916752,"totalDurationS":35455.30997874378,"totalInputTokens":141000329,"totalOutputTokens":865873,"totalCostUsd":475.55,"costSource":"official+adj"},{"split":"unlicensed/last-exam","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":28,"tasks":28,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.08321514450874437,"totalDurationS":135702.5551899186,"totalInputTokens":450451674,"totalOutputTokens":1846704,"totalCostUsd":425.56,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":29,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.08094968405781607,"totalDurationS":95778,"totalInputTokens":291906865,"totalOutputTokens":3821425,"totalCostUsd":136.99,"costSource":"db+list"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":30,"tasks":30,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.07978474570120461,"totalDurationS":48999,"totalInputTokens":84561224,"totalOutputTokens":266098,"totalCostUsd":14.4,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":30,"tasks":30,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.07960916226247187,"totalDurationS":59005,"totalInputTokens":253840806,"totalOutputTokens":675388,"totalCostUsd":39.73,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":28,"tasks":27,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.06647333333333334,"totalDurationS":140009.5,"totalInputTokens":121724035.5,"totalOutputTokens":3125973.5,"totalCostUsd":402.44,"costSource":"official"},{"split":"unlicensed/last-exam","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":25,"tasks":25,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.06638999999999999,"totalDurationS":174170,"totalInputTokens":32912598,"totalOutputTokens":542905,"totalCostUsd":158.25,"costSource":"official+adj"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":50,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.061951272828356406,"totalDurationS":169850.73263209057,"totalInputTokens":263318872.5,"totalOutputTokens":2147740,"totalCostUsd":153.78,"costSource":"db+list"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":54,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.0464254429111199,"totalDurationS":115560.64449874574,"totalInputTokens":177691032.83333334,"totalOutputTokens":1710081.8333333333,"totalCostUsd":61.08,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":50,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.043168,"totalDurationS":113242.63516030132,"totalInputTokens":116658991.5,"totalOutputTokens":1200145,"totalCostUsd":13.02,"costSource":"db+list"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":30,"tasks":28,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.03868333333333333,"totalDurationS":107122.25937282527,"totalInputTokens":959876973.5,"totalOutputTokens":1051546.5,"totalCostUsd":897.91,"costSource":"db+adj"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":29,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.03860312303344982,"totalDurationS":160106.59431680728,"totalInputTokens":403184810,"totalOutputTokens":1398987,"totalCostUsd":714.1,"costSource":"official+adj"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":54,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.03193666666666666,"totalDurationS":126648.38385215859,"totalInputTokens":189672323.5,"totalOutputTokens":1548284.1666666667,"totalCostUsd":92.25,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":31,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.029729600000000002,"totalDurationS":41655.924385556435,"totalInputTokens":56200501.5,"totalOutputTokens":477321.5,"totalCostUsd":71.44,"costSource":"list"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":52,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.029414116666666667,"totalDurationS":77991.60151617187,"totalInputTokens":44894924,"totalOutputTokens":564549.5,"totalCostUsd":20.63,"costSource":"db+list"},{"split":"unlicensed/last-exam","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":30,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.0230837,"totalDurationS":25999.22579898138,"totalInputTokens":11494377,"totalOutputTokens":127211,"totalCostUsd":36.39,"costSource":"db"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":44,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.020782483816301277,"totalDurationS":162660.51901915795,"totalInputTokens":86713583,"totalOutputTokens":1803204.5,"totalCostUsd":38.24,"costSource":"db+list"},{"split":"unlicensed/last-exam","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":43,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.016203333333333333,"totalDurationS":109949.42864178025,"totalInputTokens":86177572.5,"totalOutputTokens":1194918.8333333333,"totalCostUsd":8.37,"costSource":"db+list"},{"split":"unlicensed/last-exam","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":26,"tasks":26,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0.011556666666666666,"totalDurationS":141875,"totalInputTokens":496016340,"totalOutputTokens":813079,"totalCostUsd":729.11,"costSource":"db+list+adj"},{"split":"unlicensed/last-exam","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":30,"tasks":29,"splitTasks":30,"passes":0,"passRate":0,"avgScore":0,"totalDurationS":23240.311491120607,"totalInputTokens":58038584.5,"totalOutputTokens":1069865.5,"totalCostUsd":40.25,"costSource":"db"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":35,"passRate":0.5223880597014925,"avgScore":0.8226486188473473,"totalDurationS":93047.98500000002,"totalInputTokens":150615812,"totalOutputTokens":1446631,"totalCostUsd":272.06,"costSource":"official"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":67,"tasks":67,"splitTasks":67,"passes":32,"passRate":0.47761194029850745,"avgScore":0.8117506107197706,"totalDurationS":44003.758999999984,"totalInputTokens":139204598,"totalOutputTokens":594788,"totalCostUsd":202.7,"costSource":"official"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":67,"tasks":67,"splitTasks":67,"passes":34,"passRate":0.5074626865671642,"avgScore":0.8115622985142538,"totalDurationS":182552.064,"totalInputTokens":194978075,"totalOutputTokens":2085365,"totalCostUsd":359.87,"costSource":"official"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":67,"tasks":67,"splitTasks":67,"passes":33,"passRate":0.4925373134328358,"avgScore":0.8070988728515733,"totalDurationS":94306.28199999998,"totalInputTokens":129474576,"totalOutputTokens":1202826,"totalCostUsd":234.48,"costSource":"official"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":67,"tasks":67,"splitTasks":67,"passes":32,"passRate":0.47761194029850745,"avgScore":0.7964692243666142,"totalDurationS":57713.38899999999,"totalInputTokens":113981530,"totalOutputTokens":781431,"totalCostUsd":188.45,"costSource":"official"},{"split":"unlicensed/near-term","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":31,"passRate":0.4626865671641791,"avgScore":0.795384403782699,"totalDurationS":152327.13999999998,"totalInputTokens":702254162,"totalOutputTokens":4651765,"totalCostUsd":647.3,"costSource":"official"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":134,"tasks":67,"splitTasks":67,"passes":63,"passRate":0.47761194029850745,"avgScore":0.7882473228071811,"totalDurationS":145737.33333333334,"totalInputTokens":304163441.3333333,"totalOutputTokens":1816516,"totalCostUsd":322.09,"costSource":"list"},{"split":"unlicensed/near-term","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":66,"tasks":66,"splitTasks":67,"passes":32,"passRate":0.47761194029850745,"avgScore":0.7864883060651019,"totalDurationS":109483.99199999997,"totalInputTokens":470809193,"totalOutputTokens":3162955,"totalCostUsd":429.73,"costSource":"official"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":134,"tasks":67,"splitTasks":67,"passes":61,"passRate":0.4552238805970149,"avgScore":0.7829241382323966,"totalDurationS":125006.5,"totalInputTokens":189978516.33333334,"totalOutputTokens":1282200,"totalCostUsd":210.38,"costSource":"list"},{"split":"unlicensed/near-term","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":67,"tasks":67,"splitTasks":67,"passes":29,"passRate":0.43283582089552236,"avgScore":0.7791930500930184,"totalDurationS":60207.228,"totalInputTokens":436608868,"totalOutputTokens":4037190,"totalCostUsd":102.98,"costSource":"official"},{"split":"unlicensed/near-term","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":32,"passRate":0.47761194029850745,"avgScore":0.7781381327058974,"totalDurationS":66026.07000000002,"totalInputTokens":457986200,"totalOutputTokens":3799113,"totalCostUsd":102.58,"costSource":"official"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":132,"tasks":67,"splitTasks":67,"passes":62,"passRate":0.4701492537313433,"avgScore":0.775482331051408,"totalDurationS":120620.5,"totalInputTokens":155266763,"totalOutputTokens":1008998,"totalCostUsd":172.04,"costSource":"list"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":67,"tasks":67,"splitTasks":67,"passes":32,"passRate":0.47761194029850745,"avgScore":0.7662415009285244,"totalDurationS":44720.217000000004,"totalInputTokens":84728024,"totalOutputTokens":531724,"totalCostUsd":139.47,"costSource":"official"},{"split":"unlicensed/near-term","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":67,"tasks":67,"splitTasks":67,"passes":30,"passRate":0.44776119402985076,"avgScore":0.7650876361906394,"totalDurationS":159027.705,"totalInputTokens":761793318,"totalOutputTokens":5478458,"totalCostUsd":737.47,"costSource":"official"},{"split":"unlicensed/near-term","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":67,"tasks":67,"splitTasks":67,"passes":30,"passRate":0.44776119402985076,"avgScore":0.7589191181617984,"totalDurationS":115842.56199999998,"totalInputTokens":326611054,"totalOutputTokens":2003422,"totalCostUsd":328.27,"costSource":"official"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":33,"passRate":0.4925373134328358,"avgScore":0.7562644213793285,"totalDurationS":69711,"totalInputTokens":359705378,"totalOutputTokens":1633460,"totalCostUsd":68.71,"costSource":"list"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":134,"tasks":67,"splitTasks":67,"passes":60,"passRate":0.45273631840796025,"avgScore":0.7561914737576828,"totalDurationS":123361.5,"totalInputTokens":124228619.66666667,"totalOutputTokens":787503.5,"totalCostUsd":136.75,"costSource":"list"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":67,"tasks":67,"splitTasks":67,"passes":29,"passRate":0.43283582089552236,"avgScore":0.743547028673177,"totalDurationS":78518,"totalInputTokens":541671893,"totalOutputTokens":2191134,"totalCostUsd":95.67,"costSource":"list"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":132,"tasks":67,"splitTasks":67,"passes":58,"passRate":0.44776119402985076,"avgScore":0.7387174887795719,"totalDurationS":113197,"totalInputTokens":170739006.5,"totalOutputTokens":1313492.5,"totalCostUsd":95.88,"costSource":"list"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":132,"tasks":67,"splitTasks":67,"passes":54,"passRate":0.417910447761194,"avgScore":0.7327376744045965,"totalDurationS":133954.5,"totalInputTokens":268565325.5,"totalOutputTokens":1956342.5,"totalCostUsd":141.11,"costSource":"list"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":132,"tasks":67,"splitTasks":67,"passes":58,"passRate":0.44029850746268656,"avgScore":0.724007875487875,"totalDurationS":106336,"totalInputTokens":126210106.5,"totalOutputTokens":2256939,"totalCostUsd":170.09,"costSource":"db"},{"split":"unlicensed/near-term","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":26,"passRate":0.3880597014925373,"avgScore":0.721190499337615,"totalDurationS":224956.202,"totalInputTokens":321979548,"totalOutputTokens":4654794,"totalCostUsd":137.01,"costSource":"db"},{"split":"unlicensed/near-term","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":67,"tasks":67,"splitTasks":67,"passes":26,"passRate":0.3880597014925373,"avgScore":0.7186616124141026,"totalDurationS":75263.93899999998,"totalInputTokens":239613150,"totalOutputTokens":2034986,"totalCostUsd":121.45,"costSource":"db"},{"split":"unlicensed/near-term","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":67,"tasks":67,"splitTasks":67,"passes":27,"passRate":0.40298507462686567,"avgScore":0.7159801555439591,"totalDurationS":239761.4640000001,"totalInputTokens":270158643,"totalOutputTokens":2722015,"totalCostUsd":145.05,"costSource":"db"},{"split":"unlicensed/near-term","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":67,"tasks":67,"splitTasks":67,"passes":25,"passRate":0.373134328358209,"avgScore":0.7112863360362098,"totalDurationS":76455,"totalInputTokens":504938120,"totalOutputTokens":3626698,"totalCostUsd":1018.09,"costSource":"official"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":133,"tasks":67,"splitTasks":67,"passes":57,"passRate":0.43283582089552236,"avgScore":0.7084704112498615,"totalDurationS":144963,"totalInputTokens":155958887.5,"totalOutputTokens":1013526,"totalCostUsd":83.8,"costSource":"list"},{"split":"unlicensed/near-term","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":67,"tasks":67,"splitTasks":67,"passes":25,"passRate":0.373134328358209,"avgScore":0.7078849088375331,"totalDurationS":112965.67199999999,"totalInputTokens":239815799,"totalOutputTokens":1300434,"totalCostUsd":226.65,"costSource":"official"},{"split":"unlicensed/near-term","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":66,"tasks":66,"splitTasks":67,"passes":26,"passRate":0.3880597014925373,"avgScore":0.6968586979044264,"totalDurationS":182895.38799999998,"totalInputTokens":256675448,"totalOutputTokens":2162427,"totalCostUsd":129.35,"costSource":"db"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":67,"tasks":67,"splitTasks":67,"passes":24,"passRate":0.3582089552238806,"avgScore":0.6736742823508564,"totalDurationS":60584,"totalInputTokens":228811254,"totalOutputTokens":1065059,"totalCostUsd":46.18,"costSource":"list"},{"split":"unlicensed/near-term","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":67,"tasks":67,"splitTasks":67,"passes":22,"passRate":0.3283582089552239,"avgScore":0.6736635047623744,"totalDurationS":53801.491831077,"totalInputTokens":167219189,"totalOutputTokens":1025815,"totalCostUsd":147.52,"costSource":"db"},{"split":"unlicensed/near-term","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":65,"tasks":65,"splitTasks":67,"passes":25,"passRate":0.373134328358209,"avgScore":0.6719239733700241,"totalDurationS":148769.07770477302,"totalInputTokens":223015549,"totalOutputTokens":1462808,"totalCostUsd":218.12,"costSource":"db"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":198,"tasks":67,"splitTasks":67,"passes":77,"passRate":0.3905472636815919,"avgScore":0.670526220421849,"totalDurationS":97188.19844049853,"totalInputTokens":162729818,"totalOutputTokens":1307423.8333333333,"totalCostUsd":120.93,"costSource":"db+list"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":134,"tasks":67,"splitTasks":67,"passes":53,"passRate":0.3930348258706468,"avgScore":0.6677679137696316,"totalDurationS":96179.83333333334,"totalInputTokens":71044249.66666667,"totalOutputTokens":467625,"totalCostUsd":80.16,"costSource":"list"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":131,"tasks":67,"splitTasks":67,"passes":52,"passRate":0.3880597014925373,"avgScore":0.6595062733569761,"totalDurationS":130482.5,"totalInputTokens":84622600.5,"totalOutputTokens":590880,"totalCostUsd":47.32,"costSource":"list"},{"split":"unlicensed/near-term","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":72,"tasks":67,"splitTasks":67,"passes":24,"passRate":0.35074626865671643,"avgScore":0.6414472929875101,"totalDurationS":114531,"totalInputTokens":341718065,"totalOutputTokens":3125447.5,"totalCostUsd":947.17,"costSource":"official"},{"split":"unlicensed/near-term","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":66,"tasks":66,"splitTasks":67,"passes":29,"passRate":0.43283582089552236,"avgScore":0.6396884267777608,"totalDurationS":178788,"totalInputTokens":310513347,"totalOutputTokens":8274090,"totalCostUsd":1105.97,"costSource":"published+task-ratio"},{"split":"unlicensed/near-term","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":66,"tasks":66,"splitTasks":67,"passes":24,"passRate":0.3582089552238806,"avgScore":0.6273164650789494,"totalDurationS":151680,"totalInputTokens":201294188,"totalOutputTokens":5981020,"totalCostUsd":683.28,"costSource":"published+task-ratio"},{"split":"unlicensed/near-term","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":66,"tasks":66,"splitTasks":67,"passes":21,"passRate":0.31343283582089554,"avgScore":0.6269364006481253,"totalDurationS":120381.51676356932,"totalInputTokens":110261629,"totalOutputTokens":1648119,"totalCostUsd":557.68,"costSource":"official+adj"},{"split":"unlicensed/near-term","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":66,"tasks":66,"splitTasks":67,"passes":23,"passRate":0.34328358208955223,"avgScore":0.6229800382758721,"totalDurationS":79275,"totalInputTokens":94097065,"totalOutputTokens":1059727,"totalCostUsd":49.7,"costSource":"db+list"},{"split":"unlicensed/near-term","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":69,"tasks":66,"splitTasks":67,"passes":23,"passRate":0.3358208955223881,"avgScore":0.6228643923694662,"totalDurationS":108587.11174137115,"totalInputTokens":51827010,"totalOutputTokens":741097,"totalCostUsd":68.46,"costSource":"list"},{"split":"unlicensed/near-term","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":67,"tasks":67,"splitTasks":67,"passes":19,"passRate":0.2835820895522388,"avgScore":0.6172996937063634,"totalDurationS":156896,"totalInputTokens":190131175,"totalOutputTokens":1966191,"totalCostUsd":805.69,"costSource":"official+adj"},{"split":"unlicensed/near-term","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":69,"tasks":63,"splitTasks":67,"passes":21,"passRate":0.291044776119403,"avgScore":0.6171275522572685,"totalDurationS":57944.460609696805,"totalInputTokens":176244296.5,"totalOutputTokens":1470123,"totalCostUsd":737.55,"costSource":"official+adj"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":67,"tasks":67,"splitTasks":67,"passes":20,"passRate":0.29850746268656714,"avgScore":0.6092947556539312,"totalDurationS":67571,"totalInputTokens":90618587,"totalOutputTokens":452393,"totalCostUsd":19.45,"costSource":"list"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":131,"tasks":67,"splitTasks":67,"passes":41,"passRate":0.3208955223880597,"avgScore":0.6068743663111191,"totalDurationS":116658,"totalInputTokens":62201618.5,"totalOutputTokens":448088.5,"totalCostUsd":33.74,"costSource":"list"},{"split":"unlicensed/near-term","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":67,"tasks":67,"splitTasks":67,"passes":19,"passRate":0.2835820895522388,"avgScore":0.6045069241062173,"totalDurationS":74416.76165142255,"totalInputTokens":359152755,"totalOutputTokens":1944556,"totalCostUsd":311.72,"costSource":"official"},{"split":"unlicensed/near-term","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":66,"tasks":66,"splitTasks":67,"passes":22,"passRate":0.3283582089552239,"avgScore":0.6033126287817978,"totalDurationS":117886,"totalInputTokens":187022399,"totalOutputTokens":2708776,"totalCostUsd":204.15,"costSource":"db"},{"split":"unlicensed/near-term","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":68,"tasks":66,"splitTasks":67,"passes":19,"passRate":0.26865671641791045,"avgScore":0.6008599977646784,"totalDurationS":239417.5,"totalInputTokens":732654647,"totalOutputTokens":3149946.5,"totalCostUsd":375.61,"costSource":"db"},{"split":"unlicensed/near-term","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":66,"tasks":66,"splitTasks":67,"passes":21,"passRate":0.31343283582089554,"avgScore":0.6002555857554045,"totalDurationS":298438.2150000001,"totalInputTokens":684638103,"totalOutputTokens":6102227,"totalCostUsd":null,"costSource":null},{"split":"unlicensed/near-term","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":65,"tasks":65,"splitTasks":67,"passes":25,"passRate":0.373134328358209,"avgScore":0.598098576643749,"totalDurationS":76504,"totalInputTokens":397673605,"totalOutputTokens":2241277,"totalCostUsd":446,"costSource":"published+task-ratio"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":66,"tasks":66,"splitTasks":67,"passes":20,"passRate":0.29850746268656714,"avgScore":0.5926809886791707,"totalDurationS":48118,"totalInputTokens":81684093,"totalOutputTokens":1064184,"totalCostUsd":110.43,"costSource":"db"},{"split":"unlicensed/near-term","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":65,"tasks":65,"splitTasks":67,"passes":20,"passRate":0.29850746268656714,"avgScore":0.581507678464108,"totalDurationS":84340.52837546298,"totalInputTokens":98383491,"totalOutputTokens":962554,"totalCostUsd":105.98,"costSource":"list"},{"split":"unlicensed/near-term","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":66,"tasks":65,"splitTasks":67,"passes":19,"passRate":0.2835820895522388,"avgScore":0.5799257416141242,"totalDurationS":171722.06837378268,"totalInputTokens":201660470,"totalOutputTokens":1516121.5,"totalCostUsd":508.37,"costSource":"official+adj"},{"split":"unlicensed/near-term","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":84,"tasks":65,"splitTasks":67,"passes":30,"passRate":0.3358208955223881,"avgScore":0.578007915138166,"totalDurationS":147335.50355529715,"totalInputTokens":86038352.5,"totalOutputTokens":2379425,"totalCostUsd":68.88,"costSource":"db"},{"split":"unlicensed/near-term","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":63,"tasks":63,"splitTasks":67,"passes":15,"passRate":0.22388059701492538,"avgScore":0.5578444176897955,"totalDurationS":58636.88796496298,"totalInputTokens":120384368,"totalOutputTokens":1068334,"totalCostUsd":496.33,"costSource":"official+adj"},{"split":"unlicensed/near-term","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":65,"tasks":65,"splitTasks":67,"passes":19,"passRate":0.2835820895522388,"avgScore":0.5494600574739001,"totalDurationS":99601,"totalInputTokens":239360406,"totalOutputTokens":1099196,"totalCostUsd":341.66,"costSource":"db+list+adj"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":67,"tasks":67,"splitTasks":67,"passes":17,"passRate":0.2537313432835821,"avgScore":0.5353736949071799,"totalDurationS":36974,"totalInputTokens":28164467,"totalOutputTokens":528351,"totalCostUsd":48.16,"costSource":"db"},{"split":"unlicensed/near-term","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":67,"tasks":65,"splitTasks":67,"passes":18,"passRate":0.26119402985074625,"avgScore":0.4954053099301343,"totalDurationS":175033.16224954824,"totalInputTokens":616736935.5,"totalOutputTokens":938928.5,"totalCostUsd":574.73,"costSource":"db+adj"},{"split":"unlicensed/near-term","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":67,"tasks":67,"splitTasks":67,"passes":15,"passRate":0.22388059701492538,"avgScore":0.48273103955698327,"totalDurationS":50813,"totalInputTokens":46726983,"totalOutputTokens":263717,"totalCostUsd":10.56,"costSource":"list"},{"split":"unlicensed/near-term","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":67,"tasks":67,"splitTasks":67,"passes":12,"passRate":0.1791044776119403,"avgScore":0.4766278310546233,"totalDurationS":274026,"totalInputTokens":640770834,"totalOutputTokens":8883124,"totalCostUsd":200.78,"costSource":"db"},{"split":"unlicensed/near-term","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":63,"tasks":63,"splitTasks":67,"passes":12,"passRate":0.1791044776119403,"avgScore":0.46895390009159155,"totalDurationS":137430,"totalInputTokens":501983933,"totalOutputTokens":7323900,"totalCostUsd":246.83,"costSource":"db+list"},{"split":"unlicensed/near-term","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":130,"tasks":67,"splitTasks":67,"passes":27,"passRate":0.20149253731343283,"avgScore":0.45560963735192905,"totalDurationS":224248.87307640666,"totalInputTokens":183496122.83333334,"totalOutputTokens":1648850.5,"totalCostUsd":107.85,"costSource":"db"},{"split":"unlicensed/near-term","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":66,"tasks":66,"splitTasks":67,"passes":14,"passRate":0.208955223880597,"avgScore":0.45373662346275323,"totalDurationS":62517.515991543354,"totalInputTokens":178595579,"totalOutputTokens":684821,"totalCostUsd":66.17,"costSource":"db"},{"split":"unlicensed/near-term","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":133,"tasks":67,"splitTasks":67,"passes":28,"passRate":0.19900497512437812,"avgScore":0.4381171518153468,"totalDurationS":211812.18801494362,"totalInputTokens":208154198.33333334,"totalOutputTokens":1909336.6666666667,"totalCostUsd":109.06,"costSource":"db"},{"split":"unlicensed/near-term","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":131,"tasks":67,"splitTasks":67,"passes":17,"passRate":0.12686567164179105,"avgScore":0.36422336106940467,"totalDurationS":216764.1855777436,"totalInputTokens":259732239.16666666,"totalOutputTokens":2654193.3333333335,"totalCostUsd":89.59,"costSource":"db"},{"split":"unlicensed/near-term","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":119,"tasks":65,"splitTasks":67,"passes":19,"passRate":0.15671641791044777,"avgScore":0.3512706887636276,"totalDurationS":219933.07505434786,"totalInputTokens":118462415.5,"totalOutputTokens":2057036.5,"totalCostUsd":46.55,"costSource":"db+list"},{"split":"unlicensed/near-term","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":123,"tasks":67,"splitTasks":67,"passes":16,"passRate":0.11940298507462686,"avgScore":0.3508749428062655,"totalDurationS":157005.70431608308,"totalInputTokens":105443753,"totalOutputTokens":1528714,"totalCostUsd":12.77,"costSource":"db"},{"split":"unlicensed/near-term","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":70,"tasks":67,"splitTasks":67,"passes":7,"passRate":0.1044776119402985,"avgScore":0.3184800561555183,"totalDurationS":79155.77292464607,"totalInputTokens":99801742.5,"totalOutputTokens":1025449.5,"totalCostUsd":127.32,"costSource":"list"},{"split":"unlicensed/near-term","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":105,"tasks":67,"splitTasks":67,"passes":12,"passRate":0.1044776119402985,"avgScore":0.24547984743567736,"totalDurationS":228093.81403760775,"totalInputTokens":98237249.5,"totalOutputTokens":1413585,"totalCostUsd":8.86,"costSource":"db+list"},{"split":"unlicensed/near-term","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":123,"tasks":66,"splitTasks":67,"passes":9,"passRate":0.06716417910447761,"avgScore":0.24445086433509086,"totalDurationS":112501.3786811509,"totalInputTokens":73847551.5,"totalOutputTokens":1205923,"totalCostUsd":35.01,"costSource":"db+list"},{"split":"unlicensed/near-term","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":68,"tasks":67,"splitTasks":67,"passes":9,"passRate":0.13432835820895522,"avgScore":0.23974389265492613,"totalDurationS":84571.9589642135,"totalInputTokens":85510462,"totalOutputTokens":1248047,"totalCostUsd":56.14,"costSource":"db"},{"split":"unlicensed/near-term","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":67,"tasks":66,"splitTasks":67,"passes":4,"passRate":0.05970149253731343,"avgScore":0.17789172173062615,"totalDurationS":26068.0115799919,"totalInputTokens":26353968.5,"totalOutputTokens":242635,"totalCostUsd":82.7,"costSource":"db"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":141,"tasks":141,"splitTasks":141,"passes":52,"passRate":0.36879432624113473,"avgScore":0.6208260417791966,"totalDurationS":448067.04299999995,"totalInputTokens":394105877,"totalOutputTokens":5225794,"totalCostUsd":787.03,"costSource":"official"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":141,"tasks":141,"splitTasks":141,"passes":49,"passRate":0.3475177304964539,"avgScore":0.6077671854401283,"totalDurationS":287561.2380000002,"totalInputTokens":371380020,"totalOutputTokens":3717082,"totalCostUsd":672.34,"costSource":"official"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":141,"tasks":141,"splitTasks":141,"passes":48,"passRate":0.3404255319148936,"avgScore":0.6041127316087272,"totalDurationS":278749.57200000004,"totalInputTokens":322713382,"totalOutputTokens":3045094,"totalCostUsd":575.61,"costSource":"official"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":141,"tasks":141,"splitTasks":141,"passes":49,"passRate":0.3475177304964539,"avgScore":0.603927171087911,"totalDurationS":215282.77100000004,"totalInputTokens":312451511,"totalOutputTokens":2158009,"totalCostUsd":501.86,"costSource":"official"},{"split":"unlicensed/overall","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-xhigh","runs":141,"tasks":141,"splitTasks":141,"passes":49,"passRate":0.3475177304964539,"avgScore":0.5844936386105954,"totalDurationS":228558.01299999992,"totalInputTokens":1959131229,"totalOutputTokens":11156960,"totalCostUsd":395.79,"costSource":"official"},{"split":"unlicensed/overall","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-high","runs":139,"tasks":139,"splitTasks":141,"passes":48,"passRate":0.3404255319148936,"avgScore":0.5834754211468836,"totalDurationS":375141.539,"totalInputTokens":1352781217,"totalOutputTokens":9262715,"totalCostUsd":1312.67,"costSource":"official"},{"split":"unlicensed/overall","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-xhigh","runs":141,"tasks":141,"splitTasks":141,"passes":46,"passRate":0.3262411347517731,"avgScore":0.5828994280632535,"totalDurationS":484182.8020000001,"totalInputTokens":2035626608,"totalOutputTokens":14188637,"totalCostUsd":1926,"costSource":"official"},{"split":"unlicensed/overall","harness":"codex","model":"muse-spark-1-3","harnessVariant":"reasoning-max","runs":141,"tasks":141,"splitTasks":141,"passes":45,"passRate":0.3191489361702128,"avgScore":0.5780645318965949,"totalDurationS":240790.42300000013,"totalInputTokens":1897081797,"totalOutputTokens":10619066,"totalCostUsd":382.88,"costSource":"official"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-none","runs":141,"tasks":141,"splitTasks":141,"passes":43,"passRate":0.3049645390070922,"avgScore":0.5687211245398,"totalDurationS":170424.23500000002,"totalInputTokens":449345784,"totalOutputTokens":1514474,"totalCostUsd":601.41,"costSource":"official"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":141,"tasks":141,"splitTasks":141,"passes":45,"passRate":0.3191489361702128,"avgScore":0.5644732960303419,"totalDurationS":197574.713,"totalInputTokens":224650685,"totalOutputTokens":1456309,"totalCostUsd":362.29,"costSource":"official"},{"split":"unlicensed/overall","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-medium","runs":141,"tasks":141,"splitTasks":141,"passes":44,"passRate":0.3120567375886525,"avgScore":0.559863564039273,"totalDurationS":349828.7960000001,"totalInputTokens":1061124629,"totalOutputTokens":5717720,"totalCostUsd":996.02,"costSource":"official"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-xhigh","runs":280,"tasks":141,"splitTasks":141,"passes":92,"passRate":0.3262411347517731,"avgScore":0.5595483966613978,"totalDurationS":291953.19649999996,"totalInputTokens":652364022.1666666,"totalOutputTokens":3478380.3333333335,"totalCostUsd":656.72,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-max","runs":139,"tasks":139,"splitTasks":141,"passes":47,"passRate":0.3333333333333333,"avgScore":0.5546746675414325,"totalDurationS":466554.42300000007,"totalInputTokens":1972181022,"totalOutputTokens":13524667,"totalCostUsd":1946.38,"costSource":"official"},{"split":"unlicensed/overall","harness":"claude_code","model":"qwen-3-8-max","harnessVariant":"thinking-xhigh","runs":138,"tasks":138,"splitTasks":141,"passes":41,"passRate":0.2907801418439716,"avgScore":0.5526026381504506,"totalDurationS":622739.765,"totalInputTokens":977228809,"totalOutputTokens":10754816,"totalCostUsd":406.16,"costSource":"db"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-high","runs":278,"tasks":141,"splitTasks":141,"passes":91,"passRate":0.32978723404255317,"avgScore":0.5491172987872457,"totalDurationS":282712.47,"totalInputTokens":543170921.5,"totalOutputTokens":2693839,"totalCostUsd":525.89,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"claude_code","model":"claude-opus-5","harnessVariant":"thinking-low","runs":140,"tasks":140,"splitTasks":141,"passes":42,"passRate":0.2978723404255319,"avgScore":0.5480545146373516,"totalDurationS":361649.22099999984,"totalInputTokens":692193035,"totalOutputTokens":3791370,"totalCostUsd":703.67,"costSource":"official"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-max","runs":284,"tasks":141,"splitTasks":141,"passes":89,"passRate":0.3191489361702128,"avgScore":0.5473632833709104,"totalDurationS":311864.54466666665,"totalInputTokens":921100178.5,"totalOutputTokens":4976045.666666667,"totalCostUsd":903.28,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-medium","runs":280,"tasks":141,"splitTasks":141,"passes":87,"passRate":0.317966903073286,"avgScore":0.5430423343738866,"totalDurationS":273534.44200000004,"totalInputTokens":447187737.1666667,"totalOutputTokens":2005900.5,"totalCostUsd":424.24,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-max","runs":141,"tasks":141,"splitTasks":141,"passes":44,"passRate":0.3120567375886525,"avgScore":0.5331379784041669,"totalDurationS":199793,"totalInputTokens":2398634685,"totalOutputTokens":6446026,"totalCostUsd":371.53,"costSource":"list"},{"split":"unlicensed/overall","harness":"kimi_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":138,"tasks":138,"splitTasks":141,"passes":42,"passRate":0.2978723404255319,"avgScore":0.5303482128962862,"totalDurationS":570535.643,"totalInputTokens":941842570,"totalOutputTokens":6412623,"totalCostUsd":439.62,"costSource":"db"},{"split":"unlicensed/overall","harness":"claude_code","model":"kimi-k3","harnessVariant":"thinking-max","runs":138,"tasks":138,"splitTasks":141,"passes":40,"passRate":0.28368794326241137,"avgScore":0.5269304388437668,"totalDurationS":637061.2620000002,"totalInputTokens":881625868,"totalOutputTokens":6896011,"totalCostUsd":432.22,"costSource":"db"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-max","runs":277,"tasks":141,"splitTasks":141,"passes":81,"passRate":0.29432624113475175,"avgScore":0.5252918479026842,"totalDurationS":335753,"totalInputTokens":1147950590,"totalOutputTokens":5390942,"totalCostUsd":499.67,"costSource":"list"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-xhigh","runs":141,"tasks":141,"splitTasks":141,"passes":46,"passRate":0.3262411347517731,"avgScore":0.5206445104262789,"totalDurationS":189252,"totalInputTokens":1305756331,"totalOutputTokens":3877107,"totalCostUsd":212.65,"costSource":"list"},{"split":"unlicensed/overall","harness":"grok_build","model":"grok-4-5","harnessVariant":"reasoning-high","runs":140,"tasks":140,"splitTasks":141,"passes":39,"passRate":0.2765957446808511,"avgScore":0.5173999042242261,"totalDurationS":270855.705,"totalInputTokens":468237455,"totalOutputTokens":4689597,"totalCostUsd":235,"costSource":"db"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-xhigh","runs":277,"tasks":141,"splitTasks":141,"passes":82,"passRate":0.2978723404255319,"avgScore":0.5077329832154835,"totalDurationS":260404,"totalInputTokens":720897948,"totalOutputTokens":3526337,"totalCostUsd":331.24,"costSource":"list"},{"split":"unlicensed/overall","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":"reasoning-xhigh","runs":140,"tasks":140,"splitTasks":141,"passes":38,"passRate":0.2695035460992908,"avgScore":0.5020995075154241,"totalDurationS":196439,"totalInputTokens":1779144434,"totalOutputTokens":9163045,"totalCostUsd":3187.09,"costSource":"official"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-xhigh","runs":278,"tasks":141,"splitTasks":141,"passes":80,"passRate":0.2872340425531915,"avgScore":0.49867589404218615,"totalDurationS":287393.5,"totalInputTokens":481345798.5,"totalOutputTokens":5745106.5,"totalCostUsd":522.76,"costSource":"db"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-high","runs":276,"tasks":140,"splitTasks":141,"passes":77,"passRate":0.2801418439716312,"avgScore":0.48609115476187026,"totalDurationS":303490.11950000003,"totalInputTokens":480691367,"totalOutputTokens":2592990,"totalCostUsd":233.48,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-high","runs":141,"tasks":141,"splitTasks":141,"passes":37,"passRate":0.2624113475177305,"avgScore":0.4789918638067592,"totalDurationS":142348,"totalInputTokens":643244149,"totalOutputTokens":2416086,"totalCostUsd":116.46,"costSource":"list"},{"split":"unlicensed/overall","harness":"ale_claw","model":"gpt-5-5","harnessVariant":null,"runs":138,"tasks":138,"splitTasks":141,"passes":34,"passRate":0.24113475177304963,"avgScore":0.47658737865887824,"totalDurationS":117204.74566453496,"totalInputTokens":292991974,"totalOutputTokens":2165400,"totalCostUsd":275.26,"costSource":"db"},{"split":"unlicensed/overall","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-max","runs":139,"tasks":139,"splitTasks":141,"passes":41,"passRate":0.2907801418439716,"avgScore":0.4694146393591237,"totalDurationS":543814,"totalInputTokens":1465162311,"totalOutputTokens":20372367,"totalCostUsd":3696.61,"costSource":"published+task-ratio"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Sol","harnessVariant":"reasoning-low","runs":278,"tasks":140,"splitTasks":141,"passes":72,"passRate":0.2541371158392435,"avgScore":0.4681048909575152,"totalDurationS":242446.52566666668,"totalInputTokens":230074698.16666666,"totalOutputTokens":1175061.3333333333,"totalCostUsd":223.43,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-5-5","harnessVariant":null,"runs":412,"tasks":141,"splitTasks":141,"passes":109,"passRate":0.26122931442080377,"avgScore":0.46476081556733406,"totalDurationS":226290.44892996037,"totalInputTokens":417893865.5,"totalOutputTokens":3171073.8333333335,"totalCostUsd":339.05,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"cursor_cli","model":"claude-opus-4-7","harnessVariant":"thinking-high","runs":130,"tasks":130,"splitTasks":141,"passes":32,"passRate":0.22695035460992907,"avgScore":0.44713736097477313,"totalDurationS":209777.7502665911,"totalInputTokens":317070704,"totalOutputTokens":3915017,"totalCostUsd":1564.2,"costSource":"official+adj"},{"split":"unlicensed/overall","harness":"claude_code","model":"qwen-3-8-27b","harnessVariant":"reasoning-max","runs":138,"tasks":138,"splitTasks":141,"passes":31,"passRate":0.2198581560283688,"avgScore":0.4459353752236476,"totalDurationS":873344.9099999998,"totalInputTokens":2489228093,"totalOutputTokens":14174887,"totalCostUsd":null,"costSource":null},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-medium","runs":276,"tasks":141,"splitTasks":141,"passes":69,"passRate":0.24468085106382978,"avgScore":0.4438320139384285,"totalDurationS":284946.718,"totalInputTokens":213612416.5,"totalOutputTokens":1450871,"totalCostUsd":111.31,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"openclaw","model":"gpt-5-5","harnessVariant":null,"runs":131,"tasks":131,"splitTasks":141,"passes":33,"passRate":0.23404255319148937,"avgScore":0.44245775446794344,"totalDurationS":273966.4079745095,"totalInputTokens":403857647,"totalOutputTokens":3083904,"totalCostUsd":394.14,"costSource":"db"},{"split":"unlicensed/overall","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-xhigh","runs":140,"tasks":140,"splitTasks":141,"passes":34,"passRate":0.24113475177304963,"avgScore":0.44189296504626746,"totalDurationS":416112,"totalInputTokens":1134598082,"totalOutputTokens":15341352,"totalCostUsd":2611.28,"costSource":"published+task-ratio"},{"split":"unlicensed/overall","harness":"claude_code","model":"anthropic-claude-fable-5","harnessVariant":null,"runs":146,"tasks":138,"splitTasks":141,"passes":35,"passRate":0.24113475177304963,"avgScore":0.43941419463910386,"totalDurationS":323705.5,"totalInputTokens":745520634.5,"totalOutputTokens":8906113.5,"totalCostUsd":1828.62,"costSource":"official"},{"split":"unlicensed/overall","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":"thinking-high","runs":135,"tasks":135,"splitTasks":141,"passes":34,"passRate":0.24113475177304963,"avgScore":0.4300608344770858,"totalDurationS":267844,"totalInputTokens":1571377795,"totalOutputTokens":5621171,"totalCostUsd":1508.33,"costSource":"published+task-ratio"},{"split":"unlicensed/overall","harness":"claude_code","model":"glm-5-2","harnessVariant":"max","runs":136,"tasks":136,"splitTasks":141,"passes":31,"passRate":0.2198581560283688,"avgScore":0.4293016937371446,"totalDurationS":346433,"totalInputTokens":1263713696,"totalOutputTokens":7358995,"totalCostUsd":1057.31,"costSource":"db"},{"split":"unlicensed/overall","harness":"cursor_cli","model":"gpt-5-5","harnessVariant":null,"runs":136,"tasks":133,"splitTasks":141,"passes":33,"passRate":0.23049645390070922,"avgScore":0.42851304932922624,"totalDurationS":169469.4067363392,"totalInputTokens":128616018,"totalOutputTokens":1601327,"totalCostUsd":157.35,"costSource":"list"},{"split":"unlicensed/overall","harness":"claude_code","model":"ark-0614c","harnessVariant":null,"runs":137,"tasks":134,"splitTasks":141,"passes":29,"passRate":0.19858156028368795,"avgScore":0.42800438644840083,"totalDurationS":468168.5,"totalInputTokens":1681873223.5,"totalOutputTokens":7582602,"totalCostUsd":867.99,"costSource":"db"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Terra","harnessVariant":"reasoning-low","runs":278,"tasks":141,"splitTasks":141,"passes":60,"passRate":0.2198581560283688,"avgScore":0.42499288919011063,"totalDurationS":250208.747,"totalInputTokens":153532999,"totalOutputTokens":1050240.5,"totalCostUsd":79.42,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"cursor_cli","model":"composer-2-5","harnessVariant":null,"runs":134,"tasks":134,"splitTasks":141,"passes":31,"passRate":0.2198581560283688,"avgScore":0.42078661059033406,"totalDurationS":267485,"totalInputTokens":286472308,"totalOutputTokens":2720281,"totalCostUsd":150.04,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"ale_claw","model":"claude-opus-4-7","harnessVariant":null,"runs":138,"tasks":138,"splitTasks":141,"passes":27,"passRate":0.19148936170212766,"avgScore":0.4197333412241174,"totalDurationS":252612.16767463155,"totalInputTokens":1021079941,"totalOutputTokens":5088971,"totalCostUsd":923.69,"costSource":"official"},{"split":"unlicensed/overall","harness":"droid","model":"gpt-5-5","harnessVariant":null,"runs":134,"tasks":132,"splitTasks":141,"passes":30,"passRate":0.2127659574468085,"avgScore":0.4136390008783094,"totalDurationS":207594.6145255206,"totalInputTokens":214695571,"totalOutputTokens":2091602,"totalCostUsd":224.97,"costSource":"list"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-medium","runs":138,"tasks":138,"splitTasks":141,"passes":28,"passRate":0.19858156028368795,"avgScore":0.4114434329247684,"totalDurationS":179609,"totalInputTokens":235196044,"totalOutputTokens":2640977,"totalCostUsd":291.95,"costSource":"db"},{"split":"unlicensed/overall","harness":"claude_code","model":"claude-opus-4-8","harnessVariant":null,"runs":136,"tasks":136,"splitTasks":141,"passes":25,"passRate":0.1773049645390071,"avgScore":0.4067685680771121,"totalDurationS":466272,"totalInputTokens":307300337,"totalOutputTokens":3412910,"totalCostUsd":1328.51,"costSource":"official+adj"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-medium","runs":141,"tasks":141,"splitTasks":141,"passes":26,"passRate":0.18439716312056736,"avgScore":0.40056329147969094,"totalDurationS":140221,"totalInputTokens":223199374,"totalOutputTokens":996976,"totalCostUsd":44.72,"costSource":"list"},{"split":"unlicensed/overall","harness":"openclaw","model":"gpt-5-4","harnessVariant":null,"runs":172,"tasks":135,"splitTasks":141,"passes":40,"passRate":0.22104018912529552,"avgScore":0.39912759744833903,"totalDurationS":377603.43897103076,"totalInputTokens":418635161.1666667,"totalOutputTokens":6779006.166666667,"totalCostUsd":241.72,"costSource":"db"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-5-5","harnessVariant":"reasoning-low","runs":141,"tasks":141,"splitTasks":141,"passes":26,"passRate":0.18439716312056736,"avgScore":0.3828945809408762,"totalDurationS":108014,"totalInputTokens":96188305,"totalOutputTokens":1176916,"totalCostUsd":127.9,"costSource":"db"},{"split":"unlicensed/overall","harness":"openclaw","model":"claude-opus-4-7","harnessVariant":null,"runs":137,"tasks":136,"splitTasks":141,"passes":24,"passRate":0.1702127659574468,"avgScore":0.3745618668551661,"totalDurationS":403839.59668815427,"totalInputTokens":722150808,"totalOutputTokens":3808451.5,"totalCostUsd":1495.3,"costSource":"official+adj"},{"split":"unlicensed/overall","harness":"claude_code","model":"claude-opus-4-7","harnessVariant":null,"runs":130,"tasks":130,"splitTasks":141,"passes":21,"passRate":0.14893617021276595,"avgScore":0.3722051359473687,"totalDurationS":141696.4445367267,"totalInputTokens":380178747,"totalOutputTokens":3444699,"totalCostUsd":1558.83,"costSource":"official+adj"},{"split":"unlicensed/overall","harness":"gemini_cli","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":135,"tasks":135,"splitTasks":141,"passes":25,"passRate":0.1773049645390071,"avgScore":0.3480542170776246,"totalDurationS":317055,"totalInputTokens":1159533595,"totalOutputTokens":3389319,"totalCostUsd":1942.97,"costSource":"db+list+adj"},{"split":"unlicensed/overall","harness":"openclaw","model":"qwen-qwen3-7-max","harnessVariant":null,"runs":135,"tasks":135,"splitTasks":141,"passes":18,"passRate":0.1276595744680851,"avgScore":0.33691021666783877,"totalDurationS":312987,"totalInputTokens":1245322848,"totalOutputTokens":17017497,"totalCostUsd":603.35,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"droid","model":"claude-opus-4-7","harnessVariant":null,"runs":101,"tasks":95,"splitTasks":141,"passes":22,"passRate":0.1453900709219858,"avgScore":0.33663835749551463,"totalDurationS":99274.81146285753,"totalInputTokens":344833331.5,"totalOutputTokens":2642831,"totalCostUsd":1325.06,"costSource":"official+adj"},{"split":"unlicensed/overall","harness":"openclaw_cli","model":"ark-0614c","harnessVariant":null,"runs":140,"tasks":140,"splitTasks":141,"passes":19,"passRate":0.1347517730496454,"avgScore":0.3346469768128772,"totalDurationS":630410,"totalInputTokens":1601437068,"totalOutputTokens":20409603,"totalCostUsd":439.63,"costSource":"db"},{"split":"unlicensed/overall","harness":"codex","model":"GPT-5.6-Luna","harnessVariant":"reasoning-low","runs":141,"tasks":141,"splitTasks":141,"passes":18,"passRate":0.1276595744680851,"avgScore":0.3280611890351934,"totalDurationS":77880,"totalInputTokens":102309910,"totalOutputTokens":562218,"totalCostUsd":22.46,"costSource":"list"},{"split":"unlicensed/overall","harness":"openclaw","model":"gemini-3-1-pro-preview","harnessVariant":null,"runs":142,"tasks":134,"splitTasks":141,"passes":22,"passRate":0.1524822695035461,"avgScore":0.31130806689351526,"totalDurationS":449865.6185256547,"totalInputTokens":2913806051,"totalOutputTokens":3449466,"totalCostUsd":2624.2,"costSource":"db+adj"},{"split":"unlicensed/overall","harness":"ale_claw","model":"gpt-5-4","harnessVariant":null,"runs":137,"tasks":137,"splitTasks":141,"passes":18,"passRate":0.1276595744680851,"avgScore":0.30617200210871603,"totalDurationS":156584.72501084246,"totalInputTokens":771282392,"totalOutputTokens":1721086,"totalCostUsd":247.31,"costSource":"db"},{"split":"unlicensed/overall","harness":"openclaw","model":"deepseek-v4-pro","harnessVariant":null,"runs":267,"tasks":139,"splitTasks":141,"passes":39,"passRate":0.13356973995271867,"avgScore":0.2968980544087109,"totalDurationS":429886.8668230823,"totalInputTokens":484585706.8333333,"totalOutputTokens":4577953.166666667,"totalCostUsd":251.83,"costSource":"db"},{"split":"unlicensed/overall","harness":"openclaw","model":"glm-5-1","harnessVariant":null,"runs":251,"tasks":134,"splitTasks":141,"passes":35,"passRate":0.12411347517730496,"avgScore":0.2966678841504093,"totalDurationS":527433.7247366491,"totalInputTokens":592066637.8333334,"totalOutputTokens":5130397,"totalCostUsd":348.97,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"openclaw","model":"qwen3-6-plus","harnessVariant":null,"runs":262,"tasks":139,"splitTasks":141,"passes":25,"passRate":0.09219858156028368,"avgScore":0.26021994074929344,"totalDurationS":438548.9462786893,"totalInputTokens":618181138.6666666,"totalOutputTokens":6451781.833333333,"totalCostUsd":213.49,"costSource":"db"},{"split":"unlicensed/overall","harness":"openclaw","model":"mimo-v2-5","harnessVariant":null,"runs":251,"tasks":139,"splitTasks":141,"passes":25,"passRate":0.09219858156028368,"avgScore":0.2500876678582964,"totalDurationS":356215.3619929354,"totalInputTokens":342350334.1666667,"totalOutputTokens":3820122.8333333335,"totalCostUsd":38.49,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"openclaw","model":"kimi-k2-6","harnessVariant":null,"runs":234,"tasks":137,"splitTasks":141,"passes":25,"passRate":0.09929078014184398,"avgScore":0.2292968817611259,"totalDurationS":563409.5122970284,"totalInputTokens":293251082.5,"totalOutputTokens":5966124,"totalCostUsd":121.61,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"grok_cli","model":"grok-4-3","harnessVariant":null,"runs":142,"tasks":135,"splitTasks":141,"passes":11,"passRate":0.07801418439716312,"avgScore":0.22826886829139284,"totalDurationS":155064.3737437582,"totalInputTokens":223145635.66666666,"totalOutputTokens":2267515.6666666665,"totalCostUsd":284.6,"costSource":"list"},{"split":"unlicensed/overall","harness":"openclaw","model":"grok-4-3","harnessVariant":null,"runs":252,"tasks":138,"splitTasks":141,"passes":13,"passRate":0.04609929078014184,"avgScore":0.16924662466040963,"totalDurationS":252321.35201545496,"totalInputTokens":160417983.5,"totalOutputTokens":2603273,"totalCostUsd":75.26,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"openclaw","model":"minimax-m2-7","harnessVariant":null,"runs":216,"tasks":139,"splitTasks":141,"passes":14,"passRate":0.06382978723404255,"avgScore":0.1492606367247545,"totalDurationS":442594.7348369967,"totalInputTokens":274979228.6666667,"totalOutputTokens":3748463.1666666665,"totalCostUsd":25.31,"costSource":"db+list"},{"split":"unlicensed/overall","harness":"codex","model":"gpt-5-4","harnessVariant":null,"runs":137,"tasks":135,"splitTasks":141,"passes":11,"passRate":0.07801418439716312,"avgScore":0.13781504500323477,"totalDurationS":121711.8690922095,"totalInputTokens":168779753.5,"totalOutputTokens":2988511.5,"totalCostUsd":117.05,"costSource":"db"},{"split":"unlicensed/overall","harness":"grok_cli","model":"grok-3","harnessVariant":null,"runs":136,"tasks":134,"splitTasks":141,"passes":7,"passRate":0.04964539007092199,"avgScore":0.1351355595285674,"totalDurationS":65573.95362966345,"totalInputTokens":55532219.5,"totalOutputTokens":512410,"totalCostUsd":174.28,"costSource":"db"}]}