OpenAI · model
o1-preview benchmark scores
As of 2026-10-07, o1-preview (OpenAI) has measured scores on 3 benchmarks and estimated scores on 46 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 76.5% | measured |
| AA-HLE | 12.2% | estimated ± 4.0 pp, high confidence |
| AA-SciCode | 37.7% | estimated ± 3.2 pp, high confidence |
| Artificial Analysis Intelligence Index | 11.4% | measured |
| CritPt | 0.6% | estimated ± 2.9 pp, high confidence |
| GPQA Diamond | 72.6% | estimated ± 2.4 pp, high confidence |
| HLE | 19.4% | estimated ± 9.9 pp, low confidence |
| LiveCodeBench v6 | 78.4% | estimated ± 3.1 pp, high confidence |
| AA-Omniscience Accuracy | 18.7% | estimated ± 7.5 pp, medium confidence |
| SciCode | 37.9% | estimated ± 4.7 pp, high confidence |
| AA Coding Index | 34.1% | measured |
| BioMysteryBench (human-difficult) | 35.2% | estimated ± 8.1 pp, low confidence |
| SWE-bench Verified | 61.3% | estimated ± 5.5 pp, medium confidence |
| SWE-bench Pro | 40.4% | estimated ± 6.0 pp, medium confidence |
| MMLU-Pro | 81.7% | estimated ± 3.9 pp, high confidence |
| GPQA | 68.6% | estimated ± 3.2 pp, high confidence |
| ARC-AGI-1 | 4.8% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 1.6% | estimated ± 14.2 pp, low confidence |
| CursorBench 3.1 | 47.9% | estimated ± 4.8 pp, low confidence |
| CursorBench 3.2 | 21.3% | estimated ± 4.4 pp, medium confidence |
| FrontierCode 1.1 Main | 11.9% | estimated ± 3.8 pp, medium confidence |
| FrontierSWE v2 | 0.4% | estimated ± 14.8 pp, low confidence |
| Vals GPQA Diamond | 67.1% | estimated ± 7.4 pp, medium confidence |
| Vals MMLU-Pro | 77.0% | estimated ± 2.6 pp, low confidence |
| Vals SWE-bench | 58.5% | estimated ± 5.4 pp, medium confidence |
| CursorBench 4.0 | 8.7% | estimated ± 1.6 pp, medium confidence |
| DeepSWE | 1.6% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 15.3% | estimated ± 6.3 pp, low confidence |
| PostTrainBench v1.1 | 8.6% | estimated ± 6.1 pp, low confidence |
| Vibe Code Bench | 11.5% | estimated ± 10.3 pp, low confidence |
| C-Eval | 85.2% | estimated ± 1.0 pp, low confidence |
| MMLU-Redux | 81.3% | estimated ± 2.1 pp, low confidence |
| NL2Repo | 23.7% | estimated ± 5.1 pp, low confidence |
| SuperGPQA | 48.1% | estimated ± 10.4 pp, low confidence |
| HealthBench Hard | 0.3% | estimated ± 7.7 pp, low confidence |
| MMLU-Pro (Arcee) | 79.4% | estimated ± 5.4 pp, low confidence |
| React Native Evals | 72.6% | estimated ± 3.5 pp, high confidence |
| SWE-Rebench | 0.0% | estimated ± 8.9 pp, low confidence |
| BioMysteryBench (human-solvable) | 2.1% | estimated ± 1.0 pp, low confidence |
| FrontierCode 1.1 Extended | 32.3% | estimated ± 3.4 pp, low confidence |
| HealthBench (raw) | 17.4% | estimated ± 6.7 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 55.1% | estimated ± 4.9 pp, low confidence |
| HealthBench Professional (raw) | 27.4% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 58.3% | estimated ± 1.8 pp, low confidence |
| LiveCodeBench | 60.4% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 40.3% | estimated ± 2.8 pp, medium confidence |
| MMLU | 87.6% | estimated ± 1.9 pp, medium confidence |