{ "runId": "ddc5aa24-4d6c-4889-9348-24344c06a4ec", "generatedAt": "2026-07-11T07:43:51.757Z", "models": [ { "adapterId": "codex", "model": "gpt-5.5@medium", "label": "codex/gpt-5.5@medium", "attempts": 38, "scored": 36, "pass": 35, "partial": 1, "incorrect": 0, "protocol_error": 2, "otherErrors": 0, "passRate": 0.9722222222222222, "quality": 0.9861111111111112, "coverage": 0.9473684210526315, "fixtureScore": 0.9342105263157895, "fixtureSolveRate": 0.9210526315789473, "passAtKRate": 0.9722222222222222, "fixturesPassed": 35, "fixturesAttempted": 38, "avgDurationMs": 15101, "minDurationMs": 7214, "maxDurationMs": 24613, "totalDurationMs": 573847, "totalPromptTokens": 639908, "totalCompletionTokens": 7649, "totalReasoningTokens": 3377, "totalTokens": 647557, "totalCachedTokens": 360448, "totalCost": 0, "totalAnswerBytes": 13353, "rank": 1, "passRateLabel": "97.2%", "qualityLabel": "0.986", "coverageLabel": "94.7%", "fixtureScoreLabel": "93.4%", "fixtureSolveRateLabel": "92.1%", "passAtKLabel": "97.2%" }, { "adapterId": "codex", "model": "gpt-5.6-luna@high", "label": "codex/gpt-5.6-luna@high", "attempts": 38, "scored": 36, "pass": 35, "partial": 1, "incorrect": 0, "protocol_error": 2, "otherErrors": 0, "passRate": 0.9722222222222222, "quality": 0.9861111111111112, "coverage": 0.9473684210526315, "fixtureScore": 0.9342105263157895, "fixtureSolveRate": 0.9210526315789473, "passAtKRate": 0.9722222222222222, "fixturesPassed": 35, "fixturesAttempted": 38, "avgDurationMs": 15573, "minDurationMs": 6037, "maxDurationMs": 31937, "totalDurationMs": 591767, "totalPromptTokens": 632528, "totalCompletionTokens": 11160, "totalReasoningTokens": 7608, "totalTokens": 643688, "totalCachedTokens": 451584, "totalCost": 0, "totalAnswerBytes": 10965, "rank": 2, "passRateLabel": "97.2%", "qualityLabel": "0.986", "coverageLabel": "94.7%", "fixtureScoreLabel": "93.4%", "fixtureSolveRateLabel": "92.1%", "passAtKLabel": "97.2%" }, { "adapterId": "codex", "model": "gpt-5.6-luna@xhigh", "label": "codex/gpt-5.6-luna@xhigh", "attempts": 38, "scored": 36, "pass": 35, "partial": 1, "incorrect": 0, "protocol_error": 2, "otherErrors": 0, "passRate": 0.9722222222222222, "quality": 0.9861111111111112, "coverage": 0.9473684210526315, "fixtureScore": 0.9342105263157895, "fixtureSolveRate": 0.9210526315789473, "passAtKRate": 0.9722222222222222, "fixturesPassed": 35, "fixturesAttempted": 38, "avgDurationMs": 18291, "minDurationMs": 8364, "maxDurationMs": 58407, "totalDurationMs": 695040, "totalPromptTokens": 632616, "totalCompletionTokens": 17166, "totalReasoningTokens": 13624, "totalTokens": 649782, "totalCachedTokens": 467712, "totalCost": 0, "totalAnswerBytes": 10691, "rank": 3, "passRateLabel": "97.2%", "qualityLabel": "0.986", "coverageLabel": "94.7%", "fixtureScoreLabel": "93.4%", "fixtureSolveRateLabel": "92.1%", "passAtKLabel": "97.2%" }, { "adapterId": "codex", "model": "gpt-5.6-sol@max", "label": "codex/gpt-5.6-sol@max", "attempts": 38, "scored": 37, "pass": 34, "partial": 2, "incorrect": 1, "protocol_error": 1, "otherErrors": 0, "passRate": 0.918918918918919, "quality": 0.9459459459459459, "coverage": 0.9736842105263158, "fixtureScore": 0.9210526315789473, "fixtureSolveRate": 0.8947368421052632, "passAtKRate": 0.918918918918919, "fixturesPassed": 34, "fixturesAttempted": 38, "avgDurationMs": 18437, "minDurationMs": 5351, "maxDurationMs": 49808, "totalDurationMs": 700610, "totalPromptTokens": 677722, "totalCompletionTokens": 13461, "totalReasoningTokens": 9897, "totalTokens": 691183, "totalCachedTokens": 240128, "totalCost": 0, "totalAnswerBytes": 11161, "rank": 4, "passRateLabel": "91.9%", "qualityLabel": "0.946", "coverageLabel": "97.4%", "fixtureScoreLabel": "92.1%", "fixtureSolveRateLabel": "89.5%", "passAtKLabel": "91.9%" }, { "adapterId": "codex", "model": "gpt-5.4-mini@high", "label": "codex/gpt-5.4-mini@high", "attempts": 38, "scored": 37, "pass": 33, "partial": 3, "incorrect": 1, "protocol_error": 1, "otherErrors": 0, "passRate": 0.8918918918918919, "quality": 0.9324324324324325, "coverage": 0.9736842105263158, "fixtureScore": 0.9078947368421053, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.8918918918918919, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 9652, "minDurationMs": 4911, "maxDurationMs": 28565, "totalDurationMs": 366765, "totalPromptTokens": 552954, "totalCompletionTokens": 16280, "totalReasoningTokens": 12432, "totalTokens": 569234, "totalCachedTokens": 345600, "totalCost": 0, "totalAnswerBytes": 11537, "rank": 5, "passRateLabel": "89.2%", "qualityLabel": "0.932", "coverageLabel": "97.4%", "fixtureScoreLabel": "90.8%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "89.2%" }, { "adapterId": "codex", "model": "gpt-5.6-sol@high", "label": "codex/gpt-5.6-sol@high", "attempts": 38, "scored": 37, "pass": 33, "partial": 3, "incorrect": 1, "protocol_error": 1, "otherErrors": 0, "passRate": 0.8918918918918919, "quality": 0.9324324324324325, "coverage": 0.9736842105263158, "fixtureScore": 0.9078947368421053, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.8918918918918919, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 13292, "minDurationMs": 6195, "maxDurationMs": 19260, "totalDurationMs": 505103, "totalPromptTokens": 677710, "totalCompletionTokens": 4261, "totalReasoningTokens": 1034, "totalTokens": 681971, "totalCachedTokens": 257280, "totalCost": 0, "totalAnswerBytes": 10129, "rank": 6, "passRateLabel": "89.2%", "qualityLabel": "0.932", "coverageLabel": "97.4%", "fixtureScoreLabel": "90.8%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "89.2%" }, { "adapterId": "codex", "model": "gpt-5.6-sol@low", "label": "codex/gpt-5.6-sol@low", "attempts": 38, "scored": 37, "pass": 33, "partial": 3, "incorrect": 1, "protocol_error": 1, "otherErrors": 0, "passRate": 0.8918918918918919, "quality": 0.9324324324324325, "coverage": 0.9736842105263158, "fixtureScore": 0.9078947368421053, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.8918918918918919, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 7460, "minDurationMs": 4697, "maxDurationMs": 15649, "totalDurationMs": 283463, "totalPromptTokens": 677728, "totalCompletionTokens": 3389, "totalReasoningTokens": 302, "totalTokens": 681117, "totalCachedTokens": 171520, "totalCost": 0, "totalAnswerBytes": 9747, "rank": 7, "passRateLabel": "89.2%", "qualityLabel": "0.932", "coverageLabel": "97.4%", "fixtureScoreLabel": "90.8%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "89.2%" }, { "adapterId": "codex", "model": "gpt-5.6-sol@medium", "label": "codex/gpt-5.6-sol@medium", "attempts": 38, "scored": 37, "pass": 33, "partial": 3, "incorrect": 1, "protocol_error": 1, "otherErrors": 0, "passRate": 0.8918918918918919, "quality": 0.9324324324324325, "coverage": 0.9736842105263158, "fixtureScore": 0.9078947368421053, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.8918918918918919, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 9439, "minDurationMs": 4868, "maxDurationMs": 23290, "totalDurationMs": 358680, "totalPromptTokens": 677714, "totalCompletionTokens": 3884, "totalReasoningTokens": 805, "totalTokens": 681598, "totalCachedTokens": 240128, "totalCost": 0, "totalAnswerBytes": 9686, "rank": 8, "passRateLabel": "89.2%", "qualityLabel": "0.932", "coverageLabel": "97.4%", "fixtureScoreLabel": "90.8%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "89.2%" }, { "adapterId": "codex", "model": "gpt-5.6-terra@medium", "label": "codex/gpt-5.6-terra@medium", "attempts": 38, "scored": 37, "pass": 33, "partial": 3, "incorrect": 1, "protocol_error": 1, "otherErrors": 0, "passRate": 0.8918918918918919, "quality": 0.9324324324324325, "coverage": 0.9736842105263158, "fixtureScore": 0.9078947368421053, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.8918918918918919, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 18858, "minDurationMs": 7857, "maxDurationMs": 26788, "totalDurationMs": 716597, "totalPromptTokens": 677806, "totalCompletionTokens": 3500, "totalReasoningTokens": 35, "totalTokens": 681306, "totalCachedTokens": 300288, "totalCost": 0, "totalAnswerBytes": 11034, "rank": 9, "passRateLabel": "89.2%", "qualityLabel": "0.932", "coverageLabel": "97.4%", "fixtureScoreLabel": "90.8%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "89.2%" }, { "adapterId": "codex", "model": "gpt-5.6-terra@xhigh", "label": "codex/gpt-5.6-terra@xhigh", "attempts": 38, "scored": 37, "pass": 33, "partial": 3, "incorrect": 1, "protocol_error": 1, "otherErrors": 0, "passRate": 0.8918918918918919, "quality": 0.9324324324324325, "coverage": 0.9736842105263158, "fixtureScore": 0.9078947368421053, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.8918918918918919, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 13342, "minDurationMs": 5304, "maxDurationMs": 30884, "totalDurationMs": 506980, "totalPromptTokens": 677876, "totalCompletionTokens": 7638, "totalReasoningTokens": 4367, "totalTokens": 685514, "totalCachedTokens": 326400, "totalCost": 0, "totalAnswerBytes": 9891, "rank": 10, "passRateLabel": "89.2%", "qualityLabel": "0.932", "coverageLabel": "97.4%", "fixtureScoreLabel": "90.8%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "89.2%" }, { "adapterId": "codex", "model": "gpt-5.6-luna@medium", "label": "codex/gpt-5.6-luna@medium", "attempts": 38, "scored": 35, "pass": 34, "partial": 0, "incorrect": 1, "protocol_error": 3, "otherErrors": 0, "passRate": 0.9714285714285714, "quality": 0.9714285714285714, "coverage": 0.9210526315789473, "fixtureScore": 0.8947368421052632, "fixtureSolveRate": 0.8947368421052632, "passAtKRate": 0.9714285714285714, "fixturesPassed": 34, "fixturesAttempted": 38, "avgDurationMs": 7881, "minDurationMs": 5064, "maxDurationMs": 14484, "totalDurationMs": 299464, "totalPromptTokens": 632530, "totalCompletionTokens": 7246, "totalReasoningTokens": 3737, "totalTokens": 639776, "totalCachedTokens": 498688, "totalCost": 0, "totalAnswerBytes": 10875, "rank": 11, "passRateLabel": "97.1%", "qualityLabel": "0.971", "coverageLabel": "92.1%", "fixtureScoreLabel": "89.5%", "fixtureSolveRateLabel": "89.5%", "passAtKLabel": "97.1%" }, { "adapterId": "codex", "model": "gpt-5.6-sol@xhigh", "label": "codex/gpt-5.6-sol@xhigh", "attempts": 38, "scored": 37, "pass": 33, "partial": 2, "incorrect": 2, "protocol_error": 1, "otherErrors": 0, "passRate": 0.8918918918918919, "quality": 0.918918918918919, "coverage": 0.9736842105263158, "fixtureScore": 0.8947368421052632, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.8918918918918919, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 15436, "minDurationMs": 5754, "maxDurationMs": 53691, "totalDurationMs": 586579, "totalPromptTokens": 677780, "totalCompletionTokens": 5627, "totalReasoningTokens": 2124, "totalTokens": 683407, "totalCachedTokens": 291584, "totalCost": 0, "totalAnswerBytes": 11051, "rank": 12, "passRateLabel": "89.2%", "qualityLabel": "0.919", "coverageLabel": "97.4%", "fixtureScoreLabel": "89.5%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "89.2%" }, { "adapterId": "codex", "model": "gpt-5.6-terra@max", "label": "codex/gpt-5.6-terra@max", "attempts": 38, "scored": 37, "pass": 33, "partial": 2, "incorrect": 2, "protocol_error": 1, "otherErrors": 0, "passRate": 0.8918918918918919, "quality": 0.918918918918919, "coverage": 0.9736842105263158, "fixtureScore": 0.8947368421052632, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.8918918918918919, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 25050, "minDurationMs": 14780, "maxDurationMs": 51123, "totalDurationMs": 951891, "totalPromptTokens": 677804, "totalCompletionTokens": 14699, "totalReasoningTokens": 11418, "totalTokens": 692503, "totalCachedTokens": 326400, "totalCost": 0, "totalAnswerBytes": 9961, "rank": 13, "passRateLabel": "89.2%", "qualityLabel": "0.919", "coverageLabel": "97.4%", "fixtureScoreLabel": "89.5%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "89.2%" }, { "adapterId": "codex", "model": "gpt-5.4@medium", "label": "codex/gpt-5.4@medium", "attempts": 38, "scored": 36, "pass": 33, "partial": 2, "incorrect": 1, "protocol_error": 2, "otherErrors": 0, "passRate": 0.9166666666666666, "quality": 0.9444444444444444, "coverage": 0.9473684210526315, "fixtureScore": 0.8947368421052632, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.9166666666666666, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 15027, "minDurationMs": 6795, "maxDurationMs": 35035, "totalDurationMs": 571010, "totalPromptTokens": 566262, "totalCompletionTokens": 5866, "totalReasoningTokens": 1615, "totalTokens": 572128, "totalCachedTokens": 430080, "totalCost": 0, "totalAnswerBytes": 13360, "rank": 14, "passRateLabel": "91.7%", "qualityLabel": "0.944", "coverageLabel": "94.7%", "fixtureScoreLabel": "89.5%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "91.7%" }, { "adapterId": "codex", "model": "gpt-5.5@xhigh", "label": "codex/gpt-5.5@xhigh", "attempts": 38, "scored": 36, "pass": 33, "partial": 2, "incorrect": 1, "protocol_error": 2, "otherErrors": 0, "passRate": 0.9166666666666666, "quality": 0.9444444444444444, "coverage": 0.9473684210526315, "fixtureScore": 0.8947368421052632, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.9166666666666666, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 13648, "minDurationMs": 6271, "maxDurationMs": 19733, "totalDurationMs": 518618, "totalPromptTokens": 639976, "totalCompletionTokens": 20187, "totalReasoningTokens": 15553, "totalTokens": 660163, "totalCachedTokens": 360448, "totalCost": 0, "totalAnswerBytes": 14549, "rank": 15, "passRateLabel": "91.7%", "qualityLabel": "0.944", "coverageLabel": "94.7%", "fixtureScoreLabel": "89.5%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "91.7%" }, { "adapterId": "codex", "model": "gpt-5.6-luna@max", "label": "codex/gpt-5.6-luna@max", "attempts": 38, "scored": 36, "pass": 33, "partial": 2, "incorrect": 1, "protocol_error": 2, "otherErrors": 0, "passRate": 0.9166666666666666, "quality": 0.9444444444444444, "coverage": 0.9473684210526315, "fixtureScore": 0.8947368421052632, "fixtureSolveRate": 0.868421052631579, "passAtKRate": 0.9166666666666666, "fixturesPassed": 33, "fixturesAttempted": 38, "avgDurationMs": 16777, "minDurationMs": 7055, "maxDurationMs": 46943, "totalDurationMs": 637533, "totalPromptTokens": 632546, "totalCompletionTokens": 24243, "totalReasoningTokens": 20510, "totalTokens": 656789, "totalCachedTokens": 467712, "totalCost": 0, "totalAnswerBytes": 11587, "rank": 16, "passRateLabel": "91.7%", "qualityLabel": "0.944", "coverageLabel": "94.7%", "fixtureScoreLabel": "89.5%", "fixtureSolveRateLabel": "86.8%", "passAtKLabel": "91.7%" }, { "adapterId": "codex", "model": "gpt-5.4-mini@xhigh", "label": "codex/gpt-5.4-mini@xhigh", "attempts": 38, "scored": 36, "pass": 32, "partial": 3, "incorrect": 1, "protocol_error": 1, "otherErrors": 1, "passRate": 0.8888888888888888, "quality": 0.9305555555555556, "coverage": 0.9473684210526315, "fixtureScore": 0.881578947368421, "fixtureSolveRate": 0.8421052631578947, "passAtKRate": 0.8888888888888888, "fixturesPassed": 32, "fixturesAttempted": 38, "avgDurationMs": 36970, "minDurationMs": 6628, "maxDurationMs": 338054, "totalDurationMs": 1404857, "totalPromptTokens": 538555, "totalCompletionTokens": 49777, "totalReasoningTokens": 46118, "totalTokens": 588332, "totalCachedTokens": 345600, "totalCost": 0, "totalAnswerBytes": 10855, "rank": 17, "passRateLabel": "88.9%", "qualityLabel": "0.931", "coverageLabel": "94.7%", "fixtureScoreLabel": "88.2%", "fixtureSolveRateLabel": "84.2%", "passAtKLabel": "88.9%" }, { "adapterId": "codex", "model": "gpt-5.4-mini@low", "label": "codex/gpt-5.4-mini@low", "attempts": 38, "scored": 36, "pass": 32, "partial": 3, "incorrect": 1, "protocol_error": 2, "otherErrors": 0, "passRate": 0.8888888888888888, "quality": 0.9305555555555556, "coverage": 0.9473684210526315, "fixtureScore": 0.881578947368421, "fixtureSolveRate": 0.8421052631578947, "passAtKRate": 0.8888888888888888, "fixturesPassed": 32, "fixturesAttempted": 38, "avgDurationMs": 12539, "minDurationMs": 4507, "maxDurationMs": 16271, "totalDurationMs": 476478, "totalPromptTokens": 552964, "totalCompletionTokens": 5262, "totalReasoningTokens": 1111, "totalTokens": 558226, "totalCachedTokens": 331776, "totalCost": 0, "totalAnswerBytes": 12574, "rank": 18, "passRateLabel": "88.9%", "qualityLabel": "0.931", "coverageLabel": "94.7%", "fixtureScoreLabel": "88.2%", "fixtureSolveRateLabel": "84.2%", "passAtKLabel": "88.9%" }, { "adapterId": "codex", "model": "gpt-5.5@low", "label": "codex/gpt-5.5@low", "attempts": 38, "scored": 36, "pass": 32, "partial": 3, "incorrect": 1, "protocol_error": 2, "otherErrors": 0, "passRate": 0.8888888888888888, "quality": 0.9305555555555556, "coverage": 0.9473684210526315, "fixtureScore": 0.881578947368421, "fixtureSolveRate": 0.8421052631578947, "passAtKRate": 0.8888888888888888, "fixturesPassed": 32, "fixturesAttempted": 38, "avgDurationMs": 9485, "minDurationMs": 4955, "maxDurationMs": 19091, "totalDurationMs": 360442, "totalPromptTokens": 639904, "totalCompletionTokens": 5144, "totalReasoningTokens": 1435, "totalTokens": 645048, "totalCachedTokens": 393216, "totalCost": 0, "totalAnswerBytes": 11309, "rank": 19, "passRateLabel": "88.9%", "qualityLabel": "0.931", "coverageLabel": "94.7%", "fixtureScoreLabel": "88.2%", "fixtureSolveRateLabel": "84.2%", "passAtKLabel": "88.9%" }, { "adapterId": "codex", "model": "gpt-5.6-luna@low", "label": "codex/gpt-5.6-luna@low", "attempts": 38, "scored": 36, "pass": 32, "partial": 2, "incorrect": 2, "protocol_error": 2, "otherErrors": 0, "passRate": 0.8888888888888888, "quality": 0.9166666666666666, "coverage": 0.9473684210526315, "fixtureScore": 0.868421052631579, "fixtureSolveRate": 0.8421052631578947, "passAtKRate": 0.8888888888888888, "fixturesPassed": 32, "fixturesAttempted": 38, "avgDurationMs": 8898, "minDurationMs": 4258, "maxDurationMs": 14194, "totalDurationMs": 338133, "totalPromptTokens": 632540, "totalCompletionTokens": 5393, "totalReasoningTokens": 1930, "totalTokens": 637933, "totalCachedTokens": 451584, "totalCost": 0, "totalAnswerBytes": 10720, "rank": 20, "passRateLabel": "88.9%", "qualityLabel": "0.917", "coverageLabel": "94.7%", "fixtureScoreLabel": "86.8%", "fixtureSolveRateLabel": "84.2%", "passAtKLabel": "88.9%" }, { "adapterId": "codex", "model": "gpt-5.6-terra@high", "label": "codex/gpt-5.6-terra@high", "attempts": 38, "scored": 36, "pass": 32, "partial": 2, "incorrect": 2, "protocol_error": 2, "otherErrors": 0, "passRate": 0.8888888888888888, "quality": 0.9166666666666666, "coverage": 0.9473684210526315, "fixtureScore": 0.868421052631579, "fixtureSolveRate": 0.8421052631578947, "passAtKRate": 0.8888888888888888, "fixturesPassed": 32, "fixturesAttempted": 38, "avgDurationMs": 15723, "minDurationMs": 4854, "maxDurationMs": 42278, "totalDurationMs": 597477, "totalPromptTokens": 677808, "totalCompletionTokens": 4254, "totalReasoningTokens": 574, "totalTokens": 682062, "totalCachedTokens": 378624, "totalCost": 0, "totalAnswerBytes": 11725, "rank": 21, "passRateLabel": "88.9%", "qualityLabel": "0.917", "coverageLabel": "94.7%", "fixtureScoreLabel": "86.8%", "fixtureSolveRateLabel": "84.2%", "passAtKLabel": "88.9%" }, { "adapterId": "codex", "model": "gpt-5.4-mini@medium", "label": "codex/gpt-5.4-mini@medium", "attempts": 38, "scored": 35, "pass": 31, "partial": 3, "incorrect": 1, "protocol_error": 3, "otherErrors": 0, "passRate": 0.8857142857142857, "quality": 0.9285714285714286, "coverage": 0.9210526315789473, "fixtureScore": 0.8552631578947368, "fixtureSolveRate": 0.8157894736842105, "passAtKRate": 0.8857142857142857, "fixturesPassed": 31, "fixturesAttempted": 38, "avgDurationMs": 12771, "minDurationMs": 4679, "maxDurationMs": 20208, "totalDurationMs": 485313, "totalPromptTokens": 552956, "totalCompletionTokens": 12414, "totalReasoningTokens": 8207, "totalTokens": 565370, "totalCachedTokens": 338944, "totalCost": 0, "totalAnswerBytes": 12857, "rank": 22, "passRateLabel": "88.6%", "qualityLabel": "0.929", "coverageLabel": "92.1%", "fixtureScoreLabel": "85.5%", "fixtureSolveRateLabel": "81.6%", "passAtKLabel": "88.6%" }, { "adapterId": "codex", "model": "gpt-5.4@high", "label": "codex/gpt-5.4@high", "attempts": 38, "scored": 34, "pass": 31, "partial": 2, "incorrect": 1, "protocol_error": 4, "otherErrors": 0, "passRate": 0.9117647058823529, "quality": 0.9411764705882353, "coverage": 0.8947368421052632, "fixtureScore": 0.8421052631578947, "fixtureSolveRate": 0.8157894736842105, "passAtKRate": 0.9117647058823529, "fixturesPassed": 31, "fixturesAttempted": 38, "avgDurationMs": 12217, "minDurationMs": 6000, "maxDurationMs": 24716, "totalDurationMs": 464228, "totalPromptTokens": 566254, "totalCompletionTokens": 12757, "totalReasoningTokens": 8382, "totalTokens": 579011, "totalCachedTokens": 415744, "totalCost": 0, "totalAnswerBytes": 13434, "rank": 23, "passRateLabel": "91.2%", "qualityLabel": "0.941", "coverageLabel": "89.5%", "fixtureScoreLabel": "84.2%", "fixtureSolveRateLabel": "81.6%", "passAtKLabel": "91.2%" }, { "adapterId": "codex", "model": "gpt-5.4@xhigh", "label": "codex/gpt-5.4@xhigh", "attempts": 38, "scored": 34, "pass": 31, "partial": 2, "incorrect": 1, "protocol_error": 4, "otherErrors": 0, "passRate": 0.9117647058823529, "quality": 0.9411764705882353, "coverage": 0.8947368421052632, "fixtureScore": 0.8421052631578947, "fixtureSolveRate": 0.8157894736842105, "passAtKRate": 0.9117647058823529, "fixturesPassed": 31, "fixturesAttempted": 38, "avgDurationMs": 20294, "minDurationMs": 6888, "maxDurationMs": 58146, "totalDurationMs": 771174, "totalPromptTokens": 566326, "totalCompletionTokens": 31381, "totalReasoningTokens": 26648, "totalTokens": 597707, "totalCachedTokens": 444416, "totalCost": 0, "totalAnswerBytes": 14560, "rank": 24, "passRateLabel": "91.2%", "qualityLabel": "0.941", "coverageLabel": "89.5%", "fixtureScoreLabel": "84.2%", "fixtureSolveRateLabel": "81.6%", "passAtKLabel": "91.2%" }, { "adapterId": "codex", "model": "gpt-5.6-terra@low", "label": "codex/gpt-5.6-terra@low", "attempts": 38, "scored": 32, "pass": 31, "partial": 1, "incorrect": 0, "protocol_error": 6, "otherErrors": 0, "passRate": 0.96875, "quality": 0.984375, "coverage": 0.8421052631578947, "fixtureScore": 0.8289473684210527, "fixtureSolveRate": 0.8157894736842105, "passAtKRate": 0.96875, "fixturesPassed": 31, "fixturesAttempted": 38, "avgDurationMs": 12925, "minDurationMs": 2374, "maxDurationMs": 23112, "totalDurationMs": 491152, "totalPromptTokens": 588993, "totalCompletionTokens": 3189, "totalReasoningTokens": 0, "totalTokens": 592182, "totalCachedTokens": 235008, "totalCost": 0, "totalAnswerBytes": 10189, "rank": 25, "passRateLabel": "96.9%", "qualityLabel": "0.984", "coverageLabel": "84.2%", "fixtureScoreLabel": "82.9%", "fixtureSolveRateLabel": "81.6%", "passAtKLabel": "96.9%" }, { "adapterId": "codex", "model": "gpt-5.5@high", "label": "codex/gpt-5.5@high", "attempts": 38, "scored": 34, "pass": 30, "partial": 2, "incorrect": 2, "protocol_error": 4, "otherErrors": 0, "passRate": 0.8823529411764706, "quality": 0.9117647058823529, "coverage": 0.8947368421052632, "fixtureScore": 0.8157894736842105, "fixtureSolveRate": 0.7894736842105263, "passAtKRate": 0.8823529411764706, "fixturesPassed": 30, "fixturesAttempted": 38, "avgDurationMs": 15444, "minDurationMs": 5698, "maxDurationMs": 28116, "totalDurationMs": 586854, "totalPromptTokens": 639920, "totalCompletionTokens": 12185, "totalReasoningTokens": 7895, "totalTokens": 652105, "totalCachedTokens": 393216, "totalCost": 0, "totalAnswerBytes": 13473, "rank": 26, "passRateLabel": "88.2%", "qualityLabel": "0.912", "coverageLabel": "89.5%", "fixtureScoreLabel": "81.6%", "fixtureSolveRateLabel": "78.9%", "passAtKLabel": "88.2%" }, { "adapterId": "codex", "model": "gpt-5.4@low", "label": "codex/gpt-5.4@low", "attempts": 38, "scored": 34, "pass": 30, "partial": 1, "incorrect": 3, "protocol_error": 4, "otherErrors": 0, "passRate": 0.8823529411764706, "quality": 0.8970588235294118, "coverage": 0.8947368421052632, "fixtureScore": 0.8026315789473685, "fixtureSolveRate": 0.7894736842105263, "passAtKRate": 0.8823529411764706, "fixturesPassed": 30, "fixturesAttempted": 38, "avgDurationMs": 11951, "minDurationMs": 3969, "maxDurationMs": 17937, "totalDurationMs": 454149, "totalPromptTokens": 566256, "totalCompletionTokens": 4961, "totalReasoningTokens": 821, "totalTokens": 571217, "totalCachedTokens": 387072, "totalCost": 0, "totalAnswerBytes": 12736, "rank": 27, "passRateLabel": "88.2%", "qualityLabel": "0.897", "coverageLabel": "89.5%", "fixtureScoreLabel": "80.3%", "fixtureSolveRateLabel": "78.9%", "passAtKLabel": "88.2%" }, { "adapterId": "codex", "model": "gpt-5.3-codex-spark@low", "label": "codex/gpt-5.3-codex-spark@low", "attempts": 38, "scored": 33, "pass": 27, "partial": 5, "incorrect": 1, "protocol_error": 5, "otherErrors": 0, "passRate": 0.8181818181818182, "quality": 0.8939393939393939, "coverage": 0.868421052631579, "fixtureScore": 0.7763157894736842, "fixtureSolveRate": 0.7105263157894737, "passAtKRate": 0.8181818181818182, "fixturesPassed": 27, "fixturesAttempted": 38, "avgDurationMs": 11256, "minDurationMs": 3057, "maxDurationMs": 15067, "totalDurationMs": 427735, "totalPromptTokens": 450174, "totalCompletionTokens": 26463, "totalReasoningTokens": 20051, "totalTokens": 476637, "totalCachedTokens": 322560, "totalCost": 0, "totalAnswerBytes": 19942, "rank": 28, "passRateLabel": "81.8%", "qualityLabel": "0.894", "coverageLabel": "86.8%", "fixtureScoreLabel": "77.6%", "fixtureSolveRateLabel": "71.1%", "passAtKLabel": "81.8%" }, { "adapterId": "codex", "model": "gpt-5.3-codex-spark@xhigh", "label": "codex/gpt-5.3-codex-spark@xhigh", "attempts": 38, "scored": 31, "pass": 27, "partial": 3, "incorrect": 1, "protocol_error": 7, "otherErrors": 0, "passRate": 0.8709677419354839, "quality": 0.9193548387096774, "coverage": 0.8157894736842105, "fixtureScore": 0.75, "fixtureSolveRate": 0.7105263157894737, "passAtKRate": 0.8709677419354839, "fixturesPassed": 27, "fixturesAttempted": 38, "avgDurationMs": 12339, "minDurationMs": 3606, "maxDurationMs": 22298, "totalDurationMs": 468877, "totalPromptTokens": 450260, "totalCompletionTokens": 63268, "totalReasoningTokens": 57139, "totalTokens": 513528, "totalCachedTokens": 322560, "totalCost": 0, "totalAnswerBytes": 19216, "rank": 29, "passRateLabel": "87.1%", "qualityLabel": "0.919", "coverageLabel": "81.6%", "fixtureScoreLabel": "75.0%", "fixtureSolveRateLabel": "71.1%", "passAtKLabel": "87.1%" }, { "adapterId": "codex", "model": "gpt-5.3-codex-spark@high", "label": "codex/gpt-5.3-codex-spark@high", "attempts": 38, "scored": 30, "pass": 26, "partial": 3, "incorrect": 1, "protocol_error": 8, "otherErrors": 0, "passRate": 0.8666666666666667, "quality": 0.9166666666666666, "coverage": 0.7894736842105263, "fixtureScore": 0.7236842105263158, "fixtureSolveRate": 0.6842105263157895, "passAtKRate": 0.8666666666666667, "fixturesPassed": 26, "fixturesAttempted": 38, "avgDurationMs": 11186, "minDurationMs": 4449, "maxDurationMs": 18189, "totalDurationMs": 425061, "totalPromptTokens": 450180, "totalCompletionTokens": 55446, "totalReasoningTokens": 49192, "totalTokens": 505626, "totalCachedTokens": 311040, "totalCost": 0, "totalAnswerBytes": 19659, "rank": 30, "passRateLabel": "86.7%", "qualityLabel": "0.917", "coverageLabel": "78.9%", "fixtureScoreLabel": "72.4%", "fixtureSolveRateLabel": "68.4%", "passAtKLabel": "86.7%" }, { "adapterId": "codex", "model": "gpt-5.3-codex-spark@medium", "label": "codex/gpt-5.3-codex-spark@medium", "attempts": 38, "scored": 30, "pass": 25, "partial": 2, "incorrect": 3, "protocol_error": 8, "otherErrors": 0, "passRate": 0.8333333333333334, "quality": 0.8666666666666667, "coverage": 0.7894736842105263, "fixtureScore": 0.6842105263157895, "fixtureSolveRate": 0.6578947368421053, "passAtKRate": 0.8333333333333334, "fixturesPassed": 25, "fixturesAttempted": 38, "avgDurationMs": 5998, "minDurationMs": 3631, "maxDurationMs": 13722, "totalDurationMs": 227932, "totalPromptTokens": 450170, "totalCompletionTokens": 41956, "totalReasoningTokens": 35796, "totalTokens": 492126, "totalCachedTokens": 317184, "totalCost": 0, "totalAnswerBytes": 19089, "rank": 31, "passRateLabel": "83.3%", "qualityLabel": "0.867", "coverageLabel": "78.9%", "fixtureScoreLabel": "68.4%", "fixtureSolveRateLabel": "65.8%", "passAtKLabel": "83.3%" } ] }