OpenAI · model
o1 benchmark scores
As of 2026-10-07, o1 (OpenAI) has measured scores on 13 benchmarks and estimated scores on 55 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 74.7% | measured |
| AA-HLE | 7.0% | measured |
| AA-SciCode | 40.2% | estimated ± 3.2 pp, high confidence |
| AIME26 | 95.4% | estimated ± 0.6 pp, low confidence |
| Artificial Analysis Intelligence Index | 15.2% | measured |
| CritPt | 0.3% | measured |
| GDPval-AA | 3.6% | estimated ± 12.5 pp, low confidence |
| GPQA Diamond | 75.7% | estimated ± 0.4 pp, high confidence |
| HLE | 15.8% | estimated ± 8.2 pp, low confidence |
| IFBench | 68.9% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 65.0% | measured |
| LiveCodeBench v6 | 81.2% | estimated ± 3.1 pp, high confidence |
| AA-Omniscience Accuracy | 34.5% | measured |
| SciCode | 40.4% | estimated ± 4.7 pp, high confidence |
| IFEval | 92.2% | measured |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| τ²-bench results | 62.6% | measured |
| AA Coding Index | 39.7% | measured |
| APEX-Agents-AA | 1.6% | estimated ± 11.4 pp, low confidence |
| BioMysteryBench (human-difficult) | 37.8% | estimated ± 5.9 pp, low confidence |
| SWE-bench Verified | 68.1% | estimated ± 5.5 pp, medium confidence |
| BFCL v4 | 48.0% | estimated ± 9.8 pp, low confidence |
| SWE-bench Pro | 44.9% | estimated ± 6.0 pp, medium confidence |
| AA Agentic Index | 12.6% | estimated ± 12.3 pp, low confidence |
| MMLU-Pro | 81.7% | estimated ± 3.0 pp, high confidence |
| FrontierMath v2 (Tier 4) | 1.2% | estimated ± 4.5 pp, high confidence |
| FrontierMath v2 (Tiers 1-3) | 9.3% | measured |
| GPQA | 75.7% | measured |
| AA-IFBench | 70.3% | measured |
| AA EnterpriseOps-Gym | 6.9% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-1 | 19.2% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 11.6 pp, low confidence |
| CursorBench 3.1 | 47.9% | estimated ± 4.8 pp, low confidence |
| CursorBench 3.2 | 25.8% | estimated ± 4.4 pp, medium confidence |
| FrontierCode 1.1 Main | 14.8% | estimated ± 3.8 pp, medium confidence |
| FrontierSWE v2 | 1.0% | estimated ± 14.8 pp, low confidence |
| Vals GPQA Diamond | 63.8% | estimated ± 4.8 pp, medium confidence |
| Vals MMLU-Pro | 50.9% | estimated ± 1.2 pp, medium confidence |
| Vals SWE-bench | 62.7% | estimated ± 5.4 pp, medium confidence |
| AA ITBench | 81.3% | estimated ± 3.6 pp, low confidence |
| CursorBench 4.0 | 11.0% | estimated ± 1.6 pp, medium confidence |
| DeepSWE | 4.0% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 9.0% | estimated ± 4.9 pp, high confidence |
| PostTrainBench v1.1 | 9.0% | estimated ± 6.1 pp, low confidence |
| Vibe Code Bench | 14.7% | estimated ± 10.3 pp, low confidence |
| C-Eval | 84.6% | estimated ± 0.9 pp, low confidence |
| MCP-Tasks | 86.9% | estimated ± 8.2 pp, low confidence |
| MMAnswerBench | 82.8% | estimated ± 1.5 pp, low confidence |
| MMLU-Redux | 96.1% | estimated ± 1.1 pp, medium confidence |
| NL2Repo | 28.1% | estimated ± 5.1 pp, low confidence |
| SuperGPQA | 77.9% | estimated ± 7.5 pp, medium confidence |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| MMLU-Pro (Arcee) | 78.3% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 74.1% | estimated ± 3.5 pp, high confidence |
| SWE-Rebench | 0.1% | estimated ± 8.9 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| FrontierMath (legacy) | 10.3% | estimated ± 0.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| FrontierCode 1.1 Extended | 36.6% | estimated ± 3.4 pp, low confidence |
| HealthBench (raw) | 10.8% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 24.3% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 24.6% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 56.1% | estimated ± 1.8 pp, low confidence |
| LiveCodeBench | 73.2% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 42.8% | estimated ± 2.8 pp, medium confidence |
| MMLU | 91.8% | measured |