GPT-5.1
GPT-5.1 ranks first on 2 of the 146 benchmarks with five or more models scored.
150
Benchmarks with a score
2
Ranked first, out of five or more models
15
In the top three
OpenAI Nov 2025
GPT-5.1
Closed weights Flagship
150.9
#65 of 256
Epoch Capabilities Index
Self-Reported Index 146.6 #120 of 404
- Humanity's Last Exam 23.7% #18 /47
- SWE-bench Verified 68% #25 /32
- Terminal-Bench 2.0 47.6% #18 /43
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| IFEval | 93.5% | #3 of 60 | Official leaderboard | |
| SuperGPQA | 66.3% | #3 of 59 | Official leaderboard | |
| CL-bench | 23.7% | #2 of 24 | Official leaderboard | |
| MMLU-Pro | 86.4% | #22 of 212 | Official leaderboard | |
| LMArena (Elo) | 1,455 | #56 of 335 | Official leaderboard | |
| HELM Arabic | 81.7 | #5 of 28 | Official leaderboard | |
| CL-bench Life | 17.3% | #3 of 16 | Official leaderboard | |
| Wer wird Millionär? LLM Benchmark | 114156.0 | #15 of 77 | Official leaderboard | |
| HELM Arabic Enterprise | 73.1 | #5 of 23 | Official leaderboard | |
| Phare | 72.8% | #14 of 62 | Official leaderboard | |
| EQ-Bench 3 | 1,527 | #18 of 78 | Official leaderboard | |
| Role-play Benchmark (MiniMax) | 80.6 | #2 of 8 | Official leaderboard | |
| MultiChallenge | 63.4% | #12 of 42 | Official leaderboard | |
| MultiNRC | 49% | #11 of 38 | Official leaderboard | |
| SkateBench v2 | 71.8% | #7 of 21 | Official leaderboard | |
| BrowseComp Long Context 128k | 90% | #1 of 3 | Lab model card | |
| AMemGym | 46.5% | #4 of 11 | Official leaderboard | |
| Humanity's Last Exam | 23.7% | #18 of 47 | Official leaderboard | |
| SimpleQA Verified | 34.9% | #26 of 56 | Official leaderboard | |
| BullshitBench | 25.4% | #57 of 107 | Official leaderboard | |
| FACTS Parametric | 43.2% | #24 of 45 | Official leaderboard | |
| Visual Aesthetic Benchmark | 29.5% | #10 of 18 | Official leaderboard | |
| BullshitBench V2 | 25% | #84 of 129 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 10.9% | #71 of 104 | Official leaderboard | |
| DesignArena ASCII Art | 1,114 | #61 of 77 | Official leaderboard | |
| FACTS Search | 62.4% | #25 of 31 | Official leaderboard | |
| Document Arena | 1,416 | #38 of 39 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CMIMC 2025 | 94.4% | #4 of 33 | Official leaderboard | |
| SciArena | 1,080 | #5 of 34 | Official leaderboard | |
| SMT 2025 | 91% | #7 of 40 | Official leaderboard | |
| HMMT 2025 | 93.3% | #10 of 53 | Official leaderboard | |
| AIME 2025 | 94% | #27 of 143 | Lab model card | |
| General365 | 58.2% | #5 of 23 | Official leaderboard | |
| DTBench | 90.1% | #48 of 180 | Official leaderboard | |
| FrontierMath | 31% | #16 of 55 | Official leaderboard | |
| GPQA Diamond | 87.6% | #68 of 229 | Epoch AI run | |
| FrontierMath Tier 4 | 12.5% | #18 of 55 | Epoch AI run | |
| OTIS Mock AIME 2024-2025 | 88.6% | #75 of 212 | Epoch AI run | |
| BRUMO 2025 | 93.3% | #16 of 42 | Official leaderboard | |
| HMMT Nov 2025 | 91.7% | #9 of 22 | Official leaderboard | |
| SimpleBench | 53.2% | #54 of 106 | Official leaderboard | |
| ARC-AGI | 72.8% | #53 of 95 | Official leaderboard | |
| ARC-AGI-2 | 17.6% | #55 of 98 | Official leaderboard | |
| GPQA Main | 44.2% | #39 of 60 | Official leaderboard | |
| SGI-Bench | 29.3% | #10 of 15 | Official leaderboard | |
| ForecastBench | 0.14 | #57 of 82 | Official leaderboard | |
| MathArena Apex Shortlist | 55.9% | #27 of 38 | Official leaderboard | |
| IMO-ProofBench | 7.10% | #16 of 20 | Official leaderboard | |
| MathArena (Apex, IMO, USAMO) | 1.04% | #40 of 47 | Official leaderboard | |
| SpatialBench (LatchBio) | 39.8% | #12 of 14 | Official leaderboard | |
| Putnam 2025 | 58.0 | #4 of 4 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vibe Code Bench v1 | 24.6% | #4 of 17 | Official leaderboard | |
| WeirdML | 60.8% | #31 of 112 | Official leaderboard | |
| IOI (Vals) | 21.5% | #21 of 55 | Official leaderboard | |
| OTelBench | 14.5% | #7 of 14 | Official leaderboard | |
| ALE-Bench | 1,425 | #64 of 126 | Official leaderboard | |
| GSO-Bench | 13.7% | #16 of 30 | Official leaderboard | |
| DesignArena Game Dev | 1,169 | #77 of 143 | Official leaderboard | |
| DesignArena Data Visualization | 1,202 | #66 of 118 | Official leaderboard | |
| DesignArena Website | 1,180 | #87 of 151 | Official leaderboard | |
| DesignArena SVG | 1,139 | #62 of 103 | Official leaderboard | |
| DesignArena UI Component | 1,157 | #85 of 139 | Official leaderboard | |
| DesignArena Code | 1,161 | #89 of 143 | Official leaderboard | |
| WebDev Arena | 1,392 | #69 of 105 | arena.ai, via Epoch AI | |
| AInsteinBench | 32.9% | #4 of 6 | Official leaderboard | |
| Vibe Code Bench | 24.6% | #82 of 120 | Official leaderboard | |
| Code Arena | 1,397 | #89 of 128 | Official leaderboard | |
| DAXBench v2 | 70.4% | #35 of 47 | Official leaderboard | |
| SWE-bench Verified | 68% | #25 of 32 | Epoch AI run | |
| DesignArena 3D Design | 1,044 | #110 of 136 | Official leaderboard | |
| Image-to-WebDev Arena | 1,419 | #49 of 55 | Official leaderboard | |
| FrontierCS | 20.6 | #13 of 14 | Official leaderboard | |
| DesignArena Agentic Overall | 1,001 | #69 of 74 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Step Race | 5 | #3 of 59 | Official leaderboard | |
| SnakeBench | 33 | #20 of 188 | Official leaderboard | |
| ITBench | 55.2% | #2 of 13 | Official leaderboard | |
| GAIA | 75.8% | #12 of 64 | Official leaderboard | |
| LLM Chess | 948 | #27 of 123 | Official leaderboard | |
| Pencil Puzzle Bench | 6.70% | #19 of 53 | Official leaderboard | |
| Chess Puzzles | 42% | #35 of 93 | Epoch AI run | |
| DeR2 Bench | 81.4% | #2 of 5 | Official leaderboard | |
| Terminal-Bench 2.0 | 47.6% | #18 of 43 | Official leaderboard | |
| WorldTravel | 16.7% | #3 of 7 | Official leaderboard | |
| tau2-bench | 80.2% | #35 of 79 | Lab model card | |
| Toolathlon | 37% | #26 of 50 | Official leaderboard | |
| Agent Poker Bench | 1,039 | #9 of 17 | Official leaderboard | |
| tau2-bench Verified | 76.8% | #6 of 11 | Official leaderboard | |
| Mystery Game Puzzles | 19% | #51 of 84 | Epoch AI run | |
| LMArena Search Arena | 1,184 | #28 of 37 | Official leaderboard | |
| DeepResearch Bench | 42.8% | #17 of 22 | evals.futuresearch.ai, via Epoch AI | |
| Deep Research Bench (FutureSearch) | 0.43 | #17 of 21 | Official leaderboard | |
| MCP Atlas | 50.1% | #35 of 37 | Official leaderboard | |
| WorldGUI | 45.8% | #1 of 1 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CaseLaw v2 | 73.4% | #2 of 53 | Official leaderboard | |
| Vals Finance Agent v1 | 56.5% | #2 of 47 | Official leaderboard | |
| MedCode | 52.7% | #13 of 96 | Official leaderboard | |
| MedScribe | 88.1% | #14 of 97 | Official leaderboard | |
| LegalBench | 85.7% | #20 of 138 | Official leaderboard | |
| TaxEval v2 | 74.9% | #26 of 129 | Official leaderboard | |
| ProfBench | 54.9% | #19 of 72 | Official leaderboard | |
| Vals Finance Agent | 55.3% | #13 of 49 | Official leaderboard | |
| PRBench | 49.3% | #14 of 48 | Official leaderboard | |
| Finch (FinWorkBench) | 32% | #2 of 6 | Official leaderboard | |
| CorpFin v2 | 63.8% | #41 of 119 | Official leaderboard | |
| Vals Index v1 | 53.6% | #15 of 34 | Official leaderboard | |
| Vending-Bench | $2,380 | #5 of 9 | Official leaderboard | |
| FailureSensorIQ | 62.9% | #15 of 24 | Official leaderboard | |
| MortgageTax | 61.4% | #56 of 87 | Official leaderboard | |
| Vending-Bench 2 | $1,473 | #51 of 67 | Official leaderboard | |
| OfficeQA Pro | 15% | #11 of 12 | Official leaderboard | |
| Vending-Bench Arena | $477 | #30 of 32 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMMU | 85.4% | #1 of 136 | Official leaderboard | |
| MMMU-Pro | 79% | #6 of 57 | Official leaderboard | |
| MotionBench | 66.2% | #2 of 12 | Official leaderboard | |
| VPCT | 58.7% | #5 of 27 | VPCT leaderboard, via Epoch AI | |
| WorldVQA | 24.5% | #5 of 22 | Official leaderboard | |
| VisFactor | 30.2% | #8 of 26 | Official leaderboard | |
| Vision Arena | 1,251 | #43 of 136 | Official leaderboard | |
| RoboRewardBench | 0.90 | #7 of 22 | Official leaderboard | |
| VISTA | 43.8% | #28 of 54 | Official leaderboard | |
| ZeroBench | 6.00% | #50 of 76 | Official leaderboard | |
| Math Kangaroo 2025 (MathArena) | 76.9% | #15 of 22 | Official leaderboard | |
| CaP-X (CaP-Bench) | 10% | #7 of 10 | Official leaderboard | |
| OCR Arena | 1,367 | #9 of 11 | Official leaderboard | |
| vCX Benchmark | 81.5% | #35 of 42 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIR-Bench 2024 | 86.2% | #9 of 82 | Official leaderboard | |
| BABE | 52.3% | #1 of 6 | Official leaderboard | |
| HELM Safety | 96.8 | #14 of 75 | Official leaderboard | |
| Human Pathogen Capabilities Test | 62.9% | #18 of 86 | Official leaderboard | |
| Lakera B3 (Backbone Breaker Benchmark) | 72.9% | #8 of 35 | Official leaderboard | |
| Anthropic Red Team | 99.5% | #19 of 75 | Official leaderboard | |
| World-Class Bio | 53.2% | #23 of 74 | Official leaderboard | |
| SimpleSafetyTests | 99.8% | #26 of 75 | Official leaderboard | |
| StrongREJECT | 96.7% | #7 of 19 | Lab model card | |
| Molecular Biology Capabilities Test | 49.2% | #43 of 90 | Official leaderboard | |
| nocot-bench (NCRI) | 70.6 | #95 of 185 | Official leaderboard | |
| FORTRESS | 25.7% | #39 of 73 | Official leaderboard | |
| EvalDetectBench | 0.80 | #6 of 10 | Official leaderboard | |
| PCT (Polarized Contrastive Pairs) | 47.9% | #29 of 46 | Official leaderboard | |
| ABC Bench Liquid-Handling Robot | 5.70% | #33 of 34 | Official leaderboard | |
| InterCode-CTF | 89.7% | #2 of 2 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ACCoRD | 71.2 | #47 of 152 | Official leaderboard | |
| Conceptual Reasoning Index | 57.3 | #47 of 151 | Official leaderboard | |
| LMCA | 43.9% | #48 of 147 | Official leaderboard | |
| TutorBench | 54.1% | #7 of 20 | Official leaderboard | |
| HELM Capabilities | 65.6 | #31 of 60 | Official leaderboard | |
| CAIS Risk Index | 51.8 | #36 of 67 | Official leaderboard | |
| CAIS Text Capabilities Index | 30.7 | #37 of 68 | Official leaderboard | |
| CAIS Vision Capabilities Index | 47.4 | #33 of 53 | Official leaderboard | |
| SAGE (Vals) | 43.2% | #51 of 81 | Official leaderboard |
Its lab's numbers put it at 146.6, 4.3 points below its ECI
The Self-Reported Index fits one score to the 6 capability results OpenAI reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 143.1 to 150.0. How we compute it.
- AIME 2025 94
- GPQA Diamond 88.1
- MMMU 85.4
- tau2-bench 80.2
- SWE-bench Verified 76.3
- FrontierMath 26.7
Its lab's numbers next to 5 leaderboards
Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.
| Benchmark | Lab says | Board says | Gap |
|---|---|---|---|
| SWE-bench Verified | 76.3% SWE-bench Verified (all 500 problems) | 66% Leaderboard, medium, mini-SWE-agent | +10 pts |
| FrontierMath | 26.7% FrontierMath (with Python tool) | 31% Leaderboard, high; task version 1.1.0, Epoch | −4.3 pts |
| GPQA Diamond | 88.1% GPQA Diamond (no tools) | 87.6% Epoch AI run, high | +0.5 pts |
| AIME 2025 | 94% AIME 2025 (no tools) | 94.2% Leaderboard, high | −0.2 pts |
| MMMU | 85.4% MMMU | 85.4% Leaderboard | Same |
OpenAI's models over time
OpenAI's models in color, against every other model on the Epoch Capabilities Index, by release date.
Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 3 of them aren't in the launch post.
Robustness
- StrongREJECT 96.7