| GPQA diamondKnowledge | 92.93%claude-opus-5 Epoch AI evaluation · epoch-run Run: 2026-08-06 · gpqa_diamond.csv Reported standard error: ±1.83 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | unspecified / Epoch Inspect | Epoch AI run ↗ |
|---|
| GPQA diamondKnowledge | 87.88%claude-opus-5_low Epoch AI evaluation · epoch-run Run: 2026-08-06 · gpqa_diamond.csv Reported standard error: ±2.33 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| GPQA diamondKnowledge | 93.88%claude-opus-5_max Epoch AI evaluation · epoch-run Run: 2026-07-24 · gpqa_diamond.csv Reported standard error: ±1.48 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-Tiers-1-3-v2-PrivateReasoning | 85.61%claude-opus-5_max Epoch AI evaluation · epoch-run Run: 2026-07-24 · frontiermath_tiers_1_3_v2.csv Reported standard error: ±2.08 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-Tier-4-v2-PrivateReasoning | 73.17%claude-opus-5_max Epoch AI evaluation · epoch-run Run: 2026-07-24 · frontiermath_tier_4_v2.csv Reported standard error: ±7.01 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 93.33%claude-opus-5_low Epoch AI evaluation · epoch-run Run: 2026-08-06 · otis_mock_aime_2024_2025.csv Reported standard error: ±3.76 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 97.78%claude-opus-5 Epoch AI evaluation · epoch-run Run: 2026-08-06 · otis_mock_aime_2024_2025.csv Reported standard error: ±2.22 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | unspecified / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 98.89%claude-opus-5_max Epoch AI evaluation · epoch-run Run: 2026-07-24 · otis_mock_aime_2024_2025.csv Reported standard error: ±1.11 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| SimpleQA VerifiedKnowledge | 59.90%claude-opus-5_max Epoch AI evaluation · epoch-run Run: 2026-08-10 · simpleqa_verified.csv Reported standard error: ±1.55 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 43.00%claude-opus-5_max Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±4.98 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 27.00%claude-opus-5_low Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±4.46 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| EBR-benchOther | 45.71%claude-opus-5_max Epoch AI evaluation · epoch-run Run: 2026-09-05 · ebr_bench.csv Reported standard error: ±3.56 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| Mystery Game PuzzlesReasoning | 37.00%claude-opus-5 Epoch AI evaluation · epoch-run Run: 2026-08-06 · mystery_game_puzzles.csv Reported standard error: ±4.85 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | unspecified / Epoch Inspect | Epoch AI run ↗ |
|---|
| Mystery Game PuzzlesReasoning | 59.00%claude-opus-5_max Epoch AI evaluation · epoch-run Run: 2026-07-25 · mystery_game_puzzles.csv Reported standard error: ±4.94 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| ARC-AGIReasoning | 97.50%claude-opus-5_max https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 97.50%claude-opus-5_high https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 97.50%claude-opus-5_max https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| BalrogAgents | 63.40%claude-opus-5_max https://balrogai.com/ · external Run: Date not supplied · balrog_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| SimpleBenchReasoning | 80.60%claude-opus-5_unknown https://lmcouncil.ai/benchmarks · external Run: Date not supplied · simplebench_external.csv Inspect source ↗CC BY 4.0 | unknown / Not reported | External · via Epoch ↗ |
|---|
| WeirdMLCoding | 91.78%claude-opus-5_max https://htihle.github.io/weirdml.html · external Run: Date not supplied · weirdml_external.csv Reported standard error: ±0.00 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| WeirdMLCoding | 91.59%claude-opus-5_high https://htihle.github.io/weirdml.html · external Run: Date not supplied · weirdml_external.csv Reported standard error: ±0.00 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| WeirdMLCoding | 86.34%claude-opus-5 https://htihle.github.io/weirdml.html · external Run: Date not supplied · weirdml_external.csv Reported standard error: ±0.01 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | unspecified / Not reported | External · via Epoch ↗ |
|---|
| APEX-AgentsAgents | 65.80%claude-opus-5_max External result; evaluator not specified · external Run: Date not supplied · apex_agents_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 90.42%claude-opus-5_max External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 88.33%claude-opus-5_max External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 88.33%claude-opus-5_high External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| PostTrainBenchCoding | 35.04%claude-opus-5_unknown External result; evaluator not specified · external Run: Date not supplied · posttrainbench_external.csv Inspect source ↗CC BY 4.0 | unknown / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 46.60%claude-opus-5_max https://cursor.com/cursorbench · external Run: Date not supplied · cursorbench_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 46.10%claude-opus-5_xhigh https://cursor.com/cursorbench · external Run: Date not supplied · cursorbench_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 44.70%claude-opus-5_high https://cursor.com/cursorbench · external Run: Date not supplied · cursorbench_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 43.30%claude-opus-5_medium https://cursor.com/cursorbench · external Run: Date not supplied · cursorbench_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 40.70%claude-opus-5_low https://cursor.com/cursorbench · external Run: Date not supplied · cursorbench_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| GBAEvalOther | 79.60%claude-opus-5_unknown https://gbaeval.com/model/claude-opus-5 · external Run: Date not supplied · gbaeval_external.csv Inspect source ↗CC BY 4.0 | unknown / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 29.14%claude-opus-5_max External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 28.29%claude-opus-5_high External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 27.71%claude-opus-5_xhigh External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 26.86%claude-opus-5_medium External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 23.14%claude-opus-5_low External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| OSWorld 2.0Agents | 31.43%claude-opus-5_max https://osworld-v2.xlang.ai/ · external Run: Date not supplied · osworld_2_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| OSWorld 2.0Agents | 30.21%claude-opus-5_xhigh https://osworld-v2.xlang.ai/ · external Run: Date not supplied · osworld_2_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| OSWorld 2.0Agents | 28.98%claude-opus-5_high https://osworld-v2.xlang.ai/ · external Run: Date not supplied · osworld_2_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| OSWorld 2.0Agents | 25.33%claude-opus-5_medium https://osworld-v2.xlang.ai/ · external Run: Date not supplied · osworld_2_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| OSWorld 2.0Agents | 22.32%claude-opus-5_low https://osworld-v2.xlang.ai/ · external Run: Date not supplied · osworld_2_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| DeepSWECoding | 73.65%claude-opus-5_max https://deepswe.datacurve.ai/ · external Run: Date not supplied · deepswe_external.csv Inspect source ↗CC BY 4.0 | max / mini-swe-agent | External · via Epoch ↗ |
|---|
| DeepSWECoding | 73.15%claude-opus-5_xhigh https://deepswe.datacurve.ai/ · external Run: Date not supplied · deepswe_external.csv Inspect source ↗CC BY 4.0 | xhigh / mini-swe-agent | External · via Epoch ↗ |
|---|
| DeepSWECoding | 72.83%claude-opus-5_high https://deepswe.datacurve.ai/ · external Run: Date not supplied · deepswe_external.csv Inspect source ↗CC BY 4.0 | high / mini-swe-agent | External · via Epoch ↗ |
|---|
| DeepSWECoding | 68.90%claude-opus-5_medium https://deepswe.datacurve.ai/ · external Run: Date not supplied · deepswe_external.csv Inspect source ↗CC BY 4.0 | medium / mini-swe-agent | External · via Epoch ↗ |
|---|
| DeepSWECoding | 58.13%claude-opus-5_low https://deepswe.datacurve.ai/ · external Run: Date not supplied · deepswe_external.csv Inspect source ↗CC BY 4.0 | low / mini-swe-agent | External · via Epoch ↗ |
|---|
| ProofBenchReasoning | 99.00%claude-opus-5_max https://www.vals.ai/benchmarks/proof_bench · external Run: Date not supplied · proofbench_external.csv Reported standard error: ±1.00 pp. This is not a 90% interval. ProofBench v1.1 re-grade (vals.ai, 2026-08-14): corrected Lean formalizations + hardened grader (rejects sorry/admit shortcuts, larger elaboration budgets). Not comparable to v1.0-era values. Updated 2026-08-18 after multi-agent verification. Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| FrontierCodeCoding | 53.38%claude-opus-5_max https://cognition.com/frontiercode · external Run: Date not supplied · frontiercode_external.csv Inspect source ↗CC BY 4.0 | max / claude-code | External · via Epoch ↗ |
|---|
| LMCAReasoning | 63.30%claude-opus-5_max https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| LMCAReasoning | 64.45%claude-opus-5_xhigh https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| LMCAReasoning | 63.67%claude-opus-5_high https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| LMCAReasoning | 62.93%claude-opus-5_medium https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| LMCAReasoning | 62.58%claude-opus-5_low https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 97.60%claude-opus-5_max https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 97.87%claude-opus-5_xhigh https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 97.87%claude-opus-5_high https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 94.93%claude-opus-5_medium https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 93.07%claude-opus-5_low https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| FrontierMath-ErdosReasoning | 0.00%claude-opus-5_max Epoch AI evaluation · epoch-run Run: 2026-08-28 · frontiermath_erdos.csv Reported standard error: ±0.00 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| Furniture AssemblyReasoning | 60.83%claude-opus-5_max Epoch AI evaluation · epoch-run Run: 2026-09-10 · furniture_assembly.csv Reported standard error: ±6.19 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| GDP.pdfOther | 24.00%claude-opus-5_max https://surgehq.ai/benchmarks/gdp-pdf · external Run: Date not supplied · gdp_pdf_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| FrontierSWECoding | 52.01%claude-opus-5_max https://www.frontierswe.com/ · external Run: Date not supplied · frontierswe_external.csv Inspect source ↗CC BY 4.0 | max / proximus | External · via Epoch ↗ |
|---|
| WeirdML v3Coding | 32.54%claude-opus-5_xhigh https://htihle.github.io/weirdml.html · external Run: Date not supplied · weirdml_v3_external.csv Inspect source ↗CC BY 4.0 | xhigh / claude_code | External · via Epoch ↗ |
|---|
| Terminal-Bench 4.0Agents | 53.94%Claude Opus 5 · Claude Code · xhigh Terminal-Bench public leaderboard · benchmark-publisher Run: 2026-07-24 · 4-0-0/f7844abc-3109-4d5f-91ad-481df7b9fac2 Published model + agent result; agents differ across models. Not a controlled model-only evaluation. Reported trials: 330. Source 95% accuracy interval half-width: 3.17 pp; this is not a DC Power interval. Inspect source ↗Attributed public leaderboard score facts · Terminal-Bench | xhigh / Terminal-Bench 4.0 · Claude Code | Terminal-Bench ↗ |
|---|
| Terminal-Bench 4.0Agents | 51.82%Claude Opus 5 · Claude Code · max Terminal-Bench public leaderboard · benchmark-publisher Run: 2026-07-24 · 4-0-0/d71ac3d0-da36-49cb-89d9-323136e77111 Published model + agent result; agents differ across models. Not a controlled model-only evaluation. Reported trials: 330. Source 95% accuracy interval half-width: 3.39 pp; this is not a DC Power interval. Inspect source ↗Attributed public leaderboard score facts · Terminal-Bench | max / Terminal-Bench 4.0 · Claude Code | Terminal-Bench ↗ |
|---|
| Terminal-Bench 4.0Agents | 50.30%Claude Opus 5 · Claude Code · high Terminal-Bench public leaderboard · benchmark-publisher Run: 2026-07-24 · 4-0-0/0b2908ee-3035-447c-9876-e68fecb3f413 Published model + agent result; agents differ across models. Not a controlled model-only evaluation. Reported trials: 330. Source 95% accuracy interval half-width: 3.73 pp; this is not a DC Power interval. Inspect source ↗Attributed public leaderboard score facts · Terminal-Bench | high / Terminal-Bench 4.0 · Claude Code | Terminal-Bench ↗ |
|---|
| Terminal-Bench 4.0Agents | 44.85%Claude Opus 5 · Claude Code · medium Terminal-Bench public leaderboard · benchmark-publisher Run: 2026-07-24 · 4-0-0/8c102a88-0789-4ce7-b503-bd39e84e157b Published model + agent result; agents differ across models. Not a controlled model-only evaluation. Reported trials: 330. Source 95% accuracy interval half-width: 3.83 pp; this is not a DC Power interval. Inspect source ↗Attributed public leaderboard score facts · Terminal-Bench | medium / Terminal-Bench 4.0 · Claude Code | Terminal-Bench ↗ |
|---|
| Terminal-Bench 4.0Agents | 34.85%Claude Opus 5 · Claude Code · low Terminal-Bench public leaderboard · benchmark-publisher Run: 2026-07-24 · 4-0-0/03fe4f10-b683-427b-a820-61e38145d28b Published model + agent result; agents differ across models. Not a controlled model-only evaluation. Reported trials: 330. Source 95% accuracy interval half-width: 3.94 pp; this is not a DC Power interval. Inspect source ↗Attributed public leaderboard score facts · Terminal-Bench | low / Terminal-Bench 4.0 · Claude Code | Terminal-Bench ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 88.33%Claude Opus 5 (High) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $1.45 per task. Different from the token-workload estimate. Semi-private split only. Provider-adapter and custom-scaffold families are kept separate. Identical effort names do not imply identical compute budgets. Inspect source ↗Public leaderboard facts · ARC Prize | high / ARC Prize leaderboard baseline | ARC Prize ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 90.42%Claude Opus 5 (Max) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $2.06 per task. Different from the token-workload estimate. Semi-private split only. Provider-adapter and custom-scaffold families are kept separate. Identical effort names do not imply identical compute budgets. Inspect source ↗Public leaderboard facts · ARC Prize | max / ARC Prize leaderboard baseline | ARC Prize ↗ |
|---|