OpenAI
availableShows if the model has enough results for an index.GPT-5.1
GPT-5.1 is a reasoning model from OpenAI. 28 benchmarks count toward its score, in 7 categories.
IndexOverall score. 50 is the middle.56.4 ±3.6
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.37/s
Input / 1MUS dollars per 1M input tokens.$1.25 batch $0.625
Output / 1MUS dollars per 1M output tokens.$10 batch $5 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.400K
EloLMArena rating and rank.1423 (#100)
50 is the middle of the board. The range shows the doubt in the index. Batch work costs less.
42,982 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
28 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| AIME | Math | 93.3% | 57.2 | — | 16 Apr 2026 | Vals AI |
| MGSM | Multilingual | 93.0% | — | — | 9 Jan 2026 | Vals AI |
| OTIS Mock AIME 2024-2025 | Math | 88.6% | 61.1 | high effort | — | Epoch AI |
| GPQA diamond | Knowledge | 87.6% | 59.1 | high effort | — | Epoch AI |
| Artificial Analysis GPQA Diamond | Knowledge | 87.3% | 58.0 | — | — | Artificial Analysis |
| GPQA Diamond | Knowledge | 86.6% | 58.2 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 86.5% | 62.9 | — | 1 Sept 2026 | Vals AI |
| MMLU Pro | Knowledge | 86.4% | 56.6 | — | 1 Sept 2026 | Vals AI |
| MMMU Pro | Multimodal | 83.2% | 62.7 | — | 1 Sept 2026 | Vals AI |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 81.9% | 57.6 | — | — | Victor Barres et al. |
| Artificial Analysis Long Context Reasoning | Reasoning | 80.0% | 63.6 | — | — | Artificial Analysis |
| Artificial Analysis MMMU-Pro | Multimodal | 75.5% | 59.4 | — | — | Artificial Analysis |
| Artificial Analysis IFBench | Instruction | 72.9% | 63.1 | — | — | Artificial Analysis |
| SWE-bench | Coding | 69.8% | 53.5 | — | 1 Sept 2026 | Vals AI |
| SWE-Bench verified | Coding | 66.9% | 51.2 | high effort | — | Epoch AI |
| SWE-bench Verified | Coding | 66.0% | 50.5 | medium effort · mini-SWE-agent | 1 Sept 2026 | SWE-bench team |
| Artificial Analysis Coding Index | Coding | 49.4% | 53.8 | — | — | Artificial Analysis |
| SimpleQA Verified | Knowledge | 48.0% | 66.0 | high effort | — | Epoch AI |
| Terminal-Bench 1.0 | Agentic | 47.5% | 51.8 | — | 12 Jan 2026 | Vals AI |
| Terminal-Bench 2.0 | Agentic | 44.9% | 54.8 | — | 4 Jun 2026 | Vals AI |
| Gert Labs Composite Game Benchmark | Agentic | 41.2% | 49.2 | — | — | Gert Labs |
| Artificial Analysis Omniscience Accuracy | Knowledge | 37.7% | 60.5 | — | — | Artificial Analysis |
| Chess Puzzles | Reasoning | 32.0% | 64.9 | high effort | — | Epoch AI |
| FrontierMath-2025-02-28-Private | Math | 31.0% | 59.6 | high effort | — | Epoch AI |
| Artificial Analysis Humanity's Last Exam | Knowledge | 28.5% | 55.5 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 24.7% | 53.3 | — | — | Artificial Analysis |
| Vibe Code Bench v1.1 | Coding | 24.6% | 52.4 | OpenHands | 21 Sept 2026 | Vals AI |
| IOI v1 | Coding | 21.5% | 52.2 | — | 9 Aug 2026 | Vals AI |
| Mystery Game Puzzles | Reasoning | 16.0% | 50.9 | medium effort | — | Epoch AI |
| GDPval-AA normalized | Agentic | 15.6% | 47.5 | — | — | Artificial Analysis |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 12.5% | 57.0 | high effort | — | Epoch AI |
| Critical Physics Tasks | Reasoning | 4.9% | 48.7 | — | — | Artificial Analysis |
28 benchmarks count, from 31 of 32 results. A grey row does not count. Too few models took that benchmark.