OpenAI
GPT-5.1 benchmark results
21 results on 9 benchmarks from 4 sources.
Also listed as: gpt-5.1-high · gpt-5.1 · gpt-5.1-medium · gpt-5.1-2025-11-13_none · GPT-5.1 (no thinking) · gpt-5.1-2025-11-13_medium · GPT-5.1 (medium) · gpt-5.1-2025-11-13_high · GPT-5.1 (high) · gpt-5.1-2025-11-13_low
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1456 | 68 | Overall, style control on; 41674 votes; 95% CI 1452–1459“gpt-5.1-high” | Official leaderboard | Oct 8, 2026 |
| LMArena Text | 1439 | 98 | Overall, style control on; 44441 votes; 95% CI 1435–1442“gpt-5.1” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1395 | 93 | Overall; 4912 votes; 95% CI 1384–1407“gpt-5.1-medium” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1342 | 112 | Overall; 10716 votes; 95% CI 1333–1350“gpt-5.1” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1251 | 49 | Overall, style control on; 9842 votes; 95% CI 1244–1259“gpt-5.1-high” | Official leaderboard | Oct 2, 2026 |
| LMArena Vision | 1240 | 60 | Overall, style control on; 10795 votes; 95% CI 1232–1247“gpt-5.1” | Official leaderboard | Oct 2, 2026 |
| GPQA Diamond | 87.6% | 67 | Epoch AI run, accuracy; effort: high | Independent run | Nov 13, 2025 |
| GPQA Diamond | 85.0% | 86 | Epoch AI run, accuracy; effort: medium | Independent run | Nov 17, 2025 |
| GPQA Diamond | 66.7% | 170 | Epoch AI run, accuracy; effort: no thinking | Independent run | Aug 7, 2026 |
| MMLU-Pro | 86.4% | 24 | Overall accuracy; data source: Self-Reported | Vendor-reported | Mar 11, 2026 |
| SWE-bench Verified | 68.0% | 26 | Epoch AI run (Epoch scaffold); effort: high | Independent run | Feb 18, 2026 |
| SWE-bench Verified | 66.0% | 35 | agent: mini-SWE-agent“gpt-5.1-2025-11-13” | Official leaderboard | Nov 20, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 88.6% | 79 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: high | Independent run | Nov 13, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 85.6% | 93 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium | Independent run | Nov 17, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 63.9% | 142 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: low | Independent run | Nov 25, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 37.8% | 183 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: no thinking | Independent run | Aug 7, 2026 |
| Humanity's Last Exam | 23.7% | 19 | Compiled by Epoch AI; effort: unknown thinking | Third-party compilation via Epoch AI | Nov 13, 2025 |
| Humanity's Last Exam | 6.8% | 41 | Compiled by Epoch AI; effort: no thinking | Third-party compilation via Epoch AI | Nov 13, 2025 |
| Terminal-Bench 2.0 | 47.6% | 72 | Terminal-Bench 2.0; agent: Terminus 2; effort: medium | Official leaderboard via Epoch AI | Nov 16, 2025 |
| Terminal-Bench 2.0 | 47.6% | 72 | Terminal-Bench 2.0; agent: Terminus 2 ; effort: medium | Official leaderboard via Epoch AI | Nov 16, 2025 |
| Terminal-Bench 2.0 | 47.6% | 74 | Terminal-Bench 2.0; agent: Terminus 2; effort: unknown thinking | Official leaderboard via Epoch AI | Nov 12, 2025 |
FAQ
Where do these GPT-5.1 scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, MMLU-Pro leaderboard (TIGER-Lab), and SWE-bench leaderboards (swebench.com). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.