OpenAI · model
GPT-6.1 Sol benchmark scores
As of 2026-10-07, GPT-6.1 Sol (OpenAI) has measured scores on 26 benchmarks and estimated scores on 75 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 94.4% | estimated ± 1.2 pp, high confidence |
| AA-HLE | 52.9% | measured |
| AA-SciCode | 54.2% | measured |
| Artificial Analysis Intelligence Index | 51.8% | measured |
| CritPt | 31.7% | measured |
| GDPval-AA | 53.8% | measured |
| GPQA Diamond | 96.0% | estimated ± 1.0 pp, medium confidence |
| HLE | 60.9% | estimated ± 5.5 pp, low confidence |
| AA-LCR | 83.0% | measured |
| LiveCodeBench v6 | 95.2% | estimated ± 3.3 pp, medium confidence |
| AA-Omniscience Accuracy | 62.1% | measured |
| SciCode | 53.8% | estimated ± 3.2 pp, high confidence |
| Terminal-Bench 2.1 | 89.6% | estimated ± 3.9 pp, medium confidence |
| BrowseComp | 90.7% | estimated ± 1.8 pp, medium confidence |
| HLE w/ tools | 59.2% | estimated ± 6.1 pp, medium confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, low confidence |
| τ²-bench results | 94.1% | estimated ± 7.1 pp, low confidence |
| AA Coding Index | 76.7% | estimated ± 2.5 pp, high confidence |
| AA-MMMU-Pro | 86.0% | measured |
| APEX-Agents | 43.6% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 39.6% | estimated ± 9.1 pp, medium confidence |
| BioMysteryBench (human-difficult) | 50.1% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 90.4% | estimated ± 8.4 pp, medium confidence |
| SWE-bench Verified | 91.9% | estimated ± 5.2 pp, low confidence |
| AutomationBench | 36.1% | measured |
| BFCL v4 | 77.8% | estimated ± 2.6 pp, medium confidence |
| CyberGym | 82.1% | estimated ± 3.7 pp, high confidence |
| JobBench | 56.7% | estimated ± 8.6 pp, medium confidence |
| SWE-bench Pro | 65.7% | estimated ± 6.8 pp, medium confidence |
| WideResearch | 100.0% | estimated ± 9.1 pp, low confidence |
| AA Agentic Index | 48.8% | estimated ± 2.8 pp, high confidence |
| MMLU-Pro | 85.7% | estimated ± 3.5 pp, medium confidence |
| GPQA | 95.9% | estimated ± 0.8 pp, high confidence |
| Gert Labs | 75.9% | estimated ± 8.9 pp, low confidence |
| AA-AnalystAgent | 50.0% | measured |
| AA EnterpriseOps-Gym | 52.4% | estimated ± 1.8 pp, low confidence |
| AA Harvey LAB | 92.9% | estimated ± 2.1 pp, high confidence |
| ARC-AGI-1 | 96.5% | measured |
| ARC-AGI-2 | 94.2% | measured |
| CursorBench 3.1 | 54.4% | estimated ± 3.4 pp, medium confidence |
| CursorBench 3.2 | 60.4% | estimated ± 5.3 pp, medium confidence |
| FrontierCode 1.1 Main | 50.9% | estimated ± 3.7 pp, low confidence |
| FrontierSWE v2 | 24.6% | estimated ± 14.6 pp, low confidence |
| OfficeQA Pro | 67.7% | estimated ± 7.2 pp, medium confidence |
| OSWorld-Verified | 83.8% | estimated ± 8.7 pp, low confidence |
| Vals GPQA Diamond | 98.2% | estimated ± 1.5 pp, low confidence |
| Vals MMLU-Pro | 93.0% | estimated ± 1.5 pp, low confidence |
| Vals SWE-bench | 84.5% | estimated ± 7.6 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 78.9% | estimated ± 8.5 pp, medium confidence |
| AA AutomationBench | 64.9% | measured |
| GDP.pdf | 31.0% | measured |
| AA ITBench | 52.4% | estimated ± 3.9 pp, medium confidence |
| AA Tau3 Banking | 44.6% | estimated ± 4.4 pp, medium confidence |
| AA Terminal-Bench 2.1 | 86.8% | estimated ± 2.6 pp, high confidence |
| AA Terminal-Bench 4.0 | 56.1% | measured |
| CursorBench 4.0 | 37.3% | estimated ± 3.5 pp, high confidence |
| CWE-bench v1 | 60.2% | estimated ± 6.0 pp, medium confidence |
| DeepSWE | 71.9% | measured |
| HLE w/o tools | 52.7% | estimated ± 5.0 pp, low confidence |
| OSWorld 2.0 | 58.5% | estimated ± 13.3 pp, low confidence |
| PostTrainBench v1.1 | 40.6% | estimated ± 4.8 pp, high confidence |
| Terminal-Bench 4.0 | 59.5% | estimated ± 5.1 pp, medium confidence |
| Terminal-Bench-Science 0.1 | 57.0% | measured |
| Toolathlon-Verified | 76.9% | estimated ± 1.9 pp, medium confidence |
| CharXiv | 86.0% | estimated ± 7.5 pp, low confidence |
| CharXiv w/o tools | 86.2% | estimated ± 2.4 pp, medium confidence |
| ExploitBench | 99.7% | measured |
| ExploitGym | 35.1% | measured |
| C-Eval | 96.7% | estimated ± 1.0 pp, low confidence |
| MathVision | 89.7% | estimated ± 4.9 pp, medium confidence |
| MCP Atlas | 86.5% | estimated ± 2.7 pp, low confidence |
| MMLU-Redux | 97.9% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro | 81.8% | estimated ± 4.4 pp, low confidence |
| NL2Repo | 56.5% | estimated ± 6.5 pp, medium confidence |
| QwenClawBench | 100.0% | estimated ± 6.0 pp, low confidence |
| ScreenSpot Pro | 85.9% | estimated ± 10.7 pp, low confidence |
| SuperGPQA | 89.6% | estimated ± 7.5 pp, low confidence |
| Toolathlon | 55.9% | estimated ± 6.3 pp, medium confidence |
| ERQA | 68.9% | estimated ± 3.9 pp, medium confidence |
| HealthBench Hard | 36.2% | measured |
| MedXpertQA (MM) | 77.8% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 100.0% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 78.5% | estimated ± 4.7 pp, medium confidence |
| ResearchClawBench | 19.8% | estimated ± 2.2 pp, low confidence |
| ARC-AGI-3 | 52.7% | measured |
| BioMysteryBench (human-solvable) | 89.5% | estimated ± 0.6 pp, medium confidence |
| DRACO | 83.6% | estimated ± 3.0 pp, medium confidence |
| HealthBench (raw) | 56.7% | measured |
| HealthBench (length-adjusted) | 58.5% | measured |
| HealthBench Professional | 64.2% | measured |
| HealthBench Professional (raw) | 67.2% | measured |
| HLE-Verified | 54.6% | estimated ± 0.7 pp, low confidence |
| LABBench2 | 82.6% | estimated ± 1.3 pp, medium confidence |
| MMMU | 92.5% | estimated ± 0.9 pp, medium confidence |
| Agents' Last Exam | 57.5% | estimated ± 6.3 pp, medium confidence |
| OpenHarmony Bench | 58.8% | estimated ± 2.4 pp, high confidence |
| SEC-Bench Pro | 78.8% | measured |
| MMLU | 96.2% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro w/ Python | 85.3% | estimated ± 1.6 pp, medium confidence |
| RealWorldQA | 90.6% | estimated ± 1.2 pp, low confidence |
| OmniDocBench 1.5 | 92.0% | estimated ± 6.4 pp, low confidence |