OpenAI · model
o1 benchmark scores
As of 2026-11-21, o1 (OpenAI) has measured scores on 17 benchmarks and estimated scores on 76 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 74.7% | measured |
| AA-HLE | 7.0% | measured |
| AA-SciCode | 40.2% | estimated ± 3.4 pp, high confidence |
| AIME26 | 89.9% | estimated ± 1.4 pp, medium confidence |
| Artificial Analysis Intelligence Index | 15.2% | measured |
| CritPt | 0.3% | measured |
| GDPval-AA | 3.7% | estimated ± 11.0 pp, low confidence |
| GPQA Diamond | 75.7% | estimated ± 0.1 pp, medium confidence |
| HLE | 12.8% | estimated ± 6.5 pp, medium confidence |
| IFBench | 68.3% | estimated ± 6.6 pp, medium confidence |
| AA-LCR | 65.0% | measured |
| LiveCodeBench v6 | 82.2% | estimated ± 4.7 pp, high confidence |
| AA-Omniscience Accuracy | 34.5% | measured |
| SciCode | 40.7% | estimated ± 4.6 pp, high confidence |
| BrowseComp | 58.3% | estimated ± 13.0 pp, low confidence |
| IFEval | 92.2% | measured |
| LongBench v2 | 56.1% | estimated ± 5.5 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) | 6.5% | estimated ± 6.8 pp, low confidence |
| SWE-bench Verified | 66.2% | estimated ± 6.5 pp, medium confidence |
| BFCL v4 | 51.5% | estimated ± 8.5 pp, low confidence |
| SWE-bench Pro | 57.2% | estimated ± 4.7 pp, medium confidence |
| AA Agentic Index | 13.3% | estimated ± 12.7 pp, low confidence |
| MMLU-Pro | 85.8% | estimated ± 4.0 pp, medium confidence |
| AA-IFBench | 70.3% | measured |
| BBH | 97.7% | estimated ± 2.4 pp, low confidence |
| FailureSensorIQ | 64.0% | estimated ± 2.1 pp, high confidence |
| GPQA | 75.7% | measured |
| MMLU | 91.8% | measured |
| Vals GPQA Diamond | 73.2% | measured |
| Vals LiveCodeBench | 50.3% | measured |
| Vals MMLU-Pro | 83.5% | measured |
| MMMLU | 85.4% | estimated ± 0.7 pp, medium confidence |
| Chess Puzzles | 10.0% | measured |
| AA MMLU-Pro | 86.5% | estimated ± 0.7 pp, medium confidence |
| ARC-AGI-1 | 51.8% | estimated ± 6.5 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 10.9 pp, low confidence |
| CursorBench 3.2 | 59.1% | estimated ± 7.2 pp, low confidence |
| EBR-bench | 3.6% | estimated ± 12.7 pp, low confidence |
| FrontierCode 1.1 Main | 13.8% | estimated ± 4.6 pp, medium confidence |
| FrontierMath v2 (Tier 4) | 0.0% | estimated ± 4.0 pp, medium confidence |
| FrontierMath v2 (Tiers 1-3) | 14.7% | measured |
| FrontierSWE v2 | 0.9% | estimated ± 14.3 pp, low confidence |
| Furniture Assembly | 25.0% | estimated ± 14.1 pp, low confidence |
| MaxxBench | 34.1% | estimated ± 10.3 pp, low confidence |
| Mystery Game Puzzles | 6.3% | estimated ± 10.3 pp, low confidence |
| NYT Connections | 42.0% | estimated ± 12.6 pp, low confidence |
| Vals SWE-bench | 62.6% | estimated ± 5.5 pp, medium confidence |
| VulcanBench v3 | 76.4% | estimated ± 5.6 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 50.4% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 50.2% | estimated ± 1.1 pp, low confidence |
| FrontierPhysics | 0.0% | estimated ± 6.1 pp, low confidence |
| HLE w/o tools | 27.3% | estimated ± 4.9 pp, high confidence |
| SpireClimb | 0.0% | estimated ± 10.3 pp, low confidence |
| StealthMark | 31.4% | estimated ± 9.7 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 8.6 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| SkillsBench official leaderboard (BenchFlow) | 38.6% | estimated ± 6.2 pp, medium confidence |
| Vibe Code Bench | 14.5% | estimated ± 10.0 pp, low confidence |
| FACTS Multimodal | 32.5% | estimated ± 5.6 pp, low confidence |
| ExploitBench | 9.6% | estimated ± 13.4 pp, low confidence |
| C-Eval | 90.1% | estimated ± 1.0 pp, medium confidence |
| HMMT Feb 2026 | 80.9% | estimated ± 3.1 pp, medium confidence |
| HMMT Nov 2025 | 86.2% | estimated ± 1.5 pp, low confidence |
| MMAnswerBench | 77.5% | estimated ± 2.4 pp, low confidence |
| MMLU-Redux | 95.3% | estimated ± 0.8 pp, medium confidence |
| NL2Repo | 27.4% | estimated ± 4.7 pp, medium confidence |
| SuperGPQA | 55.7% | estimated ± 8.5 pp, low confidence |
| AA LiveCodeBench | 87.7% | estimated ± 4.7 pp, low confidence |
| HealthBench Hard | 3.5% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 78.3% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 74.1% | estimated ± 3.2 pp, high confidence |
| SWE-Rebench | 0.1% | estimated ± 8.9 pp, low confidence |
| DAYJOB | 0.4% | estimated ± 6.3 pp, low confidence |
| DAYJOB Healthcare | 0.1% | estimated ± 6.1 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (length-adjusted) | 54.1% | estimated ± 3.7 pp, medium confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| HLE-Verified | 29.0% | estimated ± 7.1 pp, low confidence |
| LABBench2 | 79.5% | estimated ± 1.8 pp, low confidence |
| ScarfBench | 24.4% | estimated ± 9.1 pp, low confidence |
| BlenderWorld (text-only) | 70.6% | estimated ± 4.0 pp, low confidence |
| Cookie-Bench | 74.0% | estimated ± 2.5 pp, low confidence |
| STEMBench | 2.5% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 38.0% | estimated ± 4.3 pp, low confidence |
| OpenHarmony Bench v1.0 | 42.8% | estimated ± 2.8 pp, medium confidence |
| SEC-Bench Pro | 16.5% | estimated ± 12.3 pp, low confidence |
| MRCRv2 | 45.4% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 60.6% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 34.1% | estimated ± 3.8 pp, low confidence |
| ExploitBench Internal Port | 0.0% | estimated ± 1.4 pp, low confidence |