{"rows":[{"split":"v1.1","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-max","runs":122,"tasks":122,"splitTasks":122,"passes":52,"passRate":0.4262295081967213,"avgScore":0.7314293819265756,"totalDurationS":360764.573,"totalInputTokens":null,"totalOutputTokens":5102451,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-xhigh","runs":122,"tasks":122,"splitTasks":122,"passes":49,"passRate":0.4016393442622951,"avgScore":0.7167674912501734,"totalDurationS":277004.897,"totalInputTokens":null,"totalOutputTokens":3861588,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"claude_code","model":"claude-opus-5-5","harnessVariant":"reasoning-max","runs":122,"tasks":122,"splitTasks":122,"passes":53,"passRate":0.4344262295081967,"avgScore":0.7160204877432247,"totalDurationS":483442.931,"totalInputTokens":null,"totalOutputTokens":21534071,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-medium","runs":122,"tasks":122,"splitTasks":122,"passes":49,"passRate":0.4016393442622951,"avgScore":0.7115833255088166,"totalDurationS":194093.195,"totalInputTokens":null,"totalOutputTokens":2602360,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-high","runs":122,"tasks":122,"splitTasks":122,"passes":47,"passRate":0.38524590163934425,"avgScore":0.710408133332075,"totalDurationS":272588.827,"totalInputTokens":null,"totalOutputTokens":3279185,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"muse_code","model":"muse-wonder-1.0","harnessVariant":"reasoning-high","runs":122,"tasks":122,"splitTasks":122,"passes":47,"passRate":0.38524590163934425,"avgScore":0.6837223234342579,"totalDurationS":419227,"totalInputTokens":null,"totalOutputTokens":4737082,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"codex","model":"gpt-6-astra","harnessVariant":"reasoning-low","runs":122,"tasks":122,"splitTasks":122,"passes":47,"passRate":0.38524590163934425,"avgScore":0.6787307783671909,"totalDurationS":188741.489,"totalInputTokens":null,"totalOutputTokens":2108769,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"ale_claw","model":"gemini-4-argon","harnessVariant":"reasoning-high","runs":122,"tasks":122,"splitTasks":122,"passes":47,"passRate":0.38524590163934425,"avgScore":0.667195334357325,"totalDurationS":305716.28,"totalInputTokens":null,"totalOutputTokens":6237086,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"kimi_code","model":"kimi-k3","harnessVariant":"reasoning-max","runs":122,"tasks":122,"splitTasks":122,"passes":43,"passRate":0.3524590163934426,"avgScore":0.6302068208675451,"totalDurationS":388087.499,"totalInputTokens":null,"totalOutputTokens":7538983,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"codex","model":"minimax-m3-1-flash","harnessVariant":"reasoning-max","runs":122,"tasks":122,"splitTasks":122,"passes":36,"passRate":0.29508196721311475,"avgScore":0.589412130288703,"totalDurationS":423426.408,"totalInputTokens":null,"totalOutputTokens":17385445,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"claude_code","model":"minimax-m3-1-flash","harnessVariant":"reasoning-max","runs":122,"tasks":122,"splitTasks":122,"passes":36,"passRate":0.29508196721311475,"avgScore":0.579203281572014,"totalDurationS":439926.405,"totalInputTokens":null,"totalOutputTokens":18112471,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"zcode","model":"glm-5.3","harnessVariant":"reasoning-max","runs":122,"tasks":122,"splitTasks":122,"passes":32,"passRate":0.26229508196721313,"avgScore":0.5438646538936561,"totalDurationS":400223,"totalInputTokens":null,"totalOutputTokens":17431104,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"codex","model":"gpt-5.6-sol","harnessVariant":"reasoning-max","runs":121,"tasks":121,"splitTasks":122,"passes":37,"passRate":0.30327868852459017,"avgScore":0.48414021136013635,"totalDurationS":282103.512,"totalInputTokens":null,"totalOutputTokens":3146469,"totalCostUsd":null,"costSource":null},{"split":"v1.1","harness":"codex","model":"gpt-5.6-luna","harnessVariant":"reasoning-none","runs":122,"tasks":122,"splitTasks":122,"passes":7,"passRate":0.05737704918032787,"avgScore":0.26485945380560433,"totalDurationS":146097.508,"totalInputTokens":null,"totalOutputTokens":1064165,"totalCostUsd":null,"costSource":null}]}