OpenAI · model
GPT-6 Sol (max) benchmark scores
As of 2026-10-07, GPT-6 Sol (max) (OpenAI) has measured scores on 9 benchmarks and estimated scores on 6 more.
| Benchmark | Score | Source |
|---|---|---|
| Terminal-Bench 2.1 | 87.8% | estimated ± 4.0 pp, high confidence |
| Terminal-Bench 4.0 | 43.9% | measured |
| Terminal-Bench Science 0.1 | 30.0% | measured |
| GPQA Diamond | 93.6% | estimated ± 1.3 pp, high confidence |
| SciCode | 57.6% | measured |
| CritPt | 30.9% | measured |
| GDP.pdf | 25.2% | measured |
| τ³-Bench Banking | 46.0% | estimated ± 2.6 pp, medium confidence |
| MMMU-Pro | 83.0% | measured |
| AA-AnalystAgent | 49.4% | estimated ± 7.8 pp, medium confidence |
| Harvey LAB | 93.7% | estimated ± 1.6 pp, low confidence |
| Humanity's Last Exam | 47.9% | measured |
| AutomationBench | 61.6% | measured |
| EnterpriseOps-Gym | 42.3% | estimated ± 6.2 pp, low confidence |
| ITBench SRE | 49.4% | measured |