| GPQA diamondKnowledge | 89.65%claude-haiku-5-5_max Epoch AI evaluation · epoch-run Run: 2026-10-09 · gpqa_diamond.csv Reported standard error: ±1.98 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 | 75.09%claude-haiku-5-5_max Epoch AI evaluation · epoch-run Run: 2026-10-07 · frontiermath_tiers_1_3_v2.csv Reported standard error: ±2.57 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-Tier-4-v2-PrivateReasoning | 46.34%claude-haiku-5-5_max Epoch AI evaluation · epoch-run Run: 2026-10-07 · frontiermath_tier_4_v2.csv Reported standard error: ±7.88 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 98.89%claude-haiku-5-5_xhigh Epoch AI evaluation · epoch-run Run: 2026-10-07 · otis_mock_aime_2024_2025.csv Reported standard error: ±0.54 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 97.22%claude-haiku-5-5_high Epoch AI evaluation · epoch-run Run: 2026-10-07 · otis_mock_aime_2024_2025.csv Reported standard error: ±1.31 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | high / Epoch Inspect | Epoch AI run ↗ |
|---|
| SimpleQA VerifiedKnowledge | 23.80%claude-haiku-5-5_max Epoch AI evaluation · epoch-run Run: 2026-10-09 · simpleqa_verified.csv Reported standard error: ±1.35 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 55.00%claude-haiku-5-5_max Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±5.00 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 24.00%claude-haiku-5-5_low Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±4.29 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| EBR-benchOther | 43.81%claude-haiku-5-5_max Epoch AI evaluation · epoch-run Run: 2026-10-09 · ebr_bench.csv Reported standard error: ±1.78 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| Mystery Game PuzzlesReasoning | 30.00%claude-haiku-5-5_max Epoch AI evaluation · epoch-run Run: 2026-10-07 · mystery_game_puzzles.csv Reported standard error: ±4.61 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| ARC-AGIReasoning | 89.00%claude-haiku-5-5_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 | 87.50%claude-haiku-5-5_xhigh https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 81.50%claude-haiku-5-5_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 | 57.33%claude-haiku-5-5_medium https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 50.33%claude-haiku-5-5_low https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| APEX-AgentsAgents | 56.10%claude-haiku-5-5_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 | 61.25%claude-haiku-5-5_xhigh External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 30.69%claude-haiku-5-5_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 ↗ |
|---|
| ARC-AGI-2Reasoning | 9.44%claude-haiku-5-5_medium External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 2.78%claude-haiku-5-5_low External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| HLEKnowledge | 30.12%claude-haiku-5-5_unknown External result; evaluator not specified · external Run: Date not supplied · hle_external.csv Reported standard error: ±1.83 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | unknown / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 48.40%claude-haiku-5-5_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 | 44.30%claude-haiku-5-5_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 | 42.30%claude-haiku-5-5_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 | 36.90%claude-haiku-5-5_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 | 30.90%claude-haiku-5-5_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 ↗ |
|---|
| CritPtOther | 22.57%claude-haiku-5-5_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 | 18.86%claude-haiku-5-5_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 | 18.57%claude-haiku-5-5_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 | 12.86%claude-haiku-5-5_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 | 9.14%claude-haiku-5-5_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 ↗ |
|---|
| ProofBenchReasoning | 89.00%claude-haiku-5-5_max https://www.vals.ai/benchmarks/proof_bench · external Run: Date not supplied · proofbench_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| FrontierCodeCoding | 46.36%claude-haiku-5-5_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 | 51.06%claude-haiku-5-5_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 | 47.99%claude-haiku-5-5_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 | 45.20%claude-haiku-5-5_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 | 45.60%claude-haiku-5-5_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 | 44.83%claude-haiku-5-5_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 ↗ |
|---|
| LMCAReasoning | 39.26%claude-haiku-5-5_none https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | none / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 94.99%claude-haiku-5-5_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 | 87.20%claude-haiku-5-5_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 | 86.67%claude-haiku-5-5_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 | 84.27%claude-haiku-5-5_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 | 81.07%claude-haiku-5-5_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 ↗ |
|---|
| DTBenchReasoning | 75.20%claude-haiku-5-5_none https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | none / Not reported | External · via Epoch ↗ |
|---|
| Furniture AssemblyReasoning | 47.50%claude-haiku-5-5_max Epoch AI evaluation · epoch-run Run: 2026-10-07 · furniture_assembly.csv Reported standard error: ±6.45 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierSWECoding | 43.77%claude-haiku-5-5_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 | 24.13%claude-haiku-5-5_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 ↗ |
|---|
| LiveBench 2 Coding · 20261025Coding | 91.40%claude-haiku-5.5 · max · LiveBench 2 20261025 LiveBench · independent-run Run: Date not supplied · 20261025/table.csv Benchmark edition 25 October 2026; individual run date not supplied. One run per model; mean task score. Failed/unmeasurable tasks score zero in the source. Source effort metadata is preserved. Inspect source ↗Attributed public leaderboard score facts · LiveBench | max / LiveBench 2 · 20261025 | LiveBench ↗ |
|---|
| LiveBench 2 Reasoning · 20261025Reasoning | 82.40%claude-haiku-5.5 · max · LiveBench 2 20261025 LiveBench · independent-run Run: Date not supplied · 20261025/table.csv Benchmark edition 25 October 2026; individual run date not supplied. One run per model; mean task score. Failed/unmeasurable tasks score zero in the source. Source effort metadata is preserved. Inspect source ↗Attributed public leaderboard score facts · LiveBench | max / LiveBench 2 · 20261025 | LiveBench ↗ |
|---|
| LiveBench 2 Long Agentic · 20261025Agents | 40.00%claude-haiku-5.5 · max · LiveBench 2 20261025 LiveBench · independent-run Run: Date not supplied · 20261025/table.csv Benchmark edition 25 October 2026; individual run date not supplied. One run per model; mean task score. Failed/unmeasurable tasks score zero in the source. Source effort metadata is preserved. Inspect source ↗Attributed public leaderboard score facts · LiveBench | max / LiveBench 2 · 20261025 | LiveBench ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 61.25%Claude Haiku 5.5 (XHigh) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.084989 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 | xhigh / ARC Prize leaderboard baseline | ARC Prize ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 30.69%Claude Haiku 5.5 (High) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.046678 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 | 9.44%Claude Haiku 5.5 (Medium) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.014975 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 | medium / ARC Prize leaderboard baseline | ARC Prize ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 2.78%Claude Haiku 5.5 (Low) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.007986 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 | low / ARC Prize leaderboard baseline | ARC Prize ↗ |
|---|