GPT-4.1 ranks first on Galileo Agent Leaderboard v2.
Closed weights Flagship
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.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench-CN v1.1 | 86.2% | #9 of 178 | Official leaderboard | |
| ECLeKTic | 34.2% | #5 of 35 | Official leaderboard | |
| BuzzBench | 67.1 | #4 of 23 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 5.60% | #21 of 104 | Official leaderboard | |
| FaithJudge | 11.9% | #8 of 37 | Official leaderboard | |
| MMLU-Pro | 81.8% | #48 of 212 | Official leaderboard | |
| HELM Arabic | 81.4 | #7 of 28 | Official leaderboard | |
| LMArena (Elo) | 1,415 | #111 of 333 | Official leaderboard | |
| RewardBench 2 | 72.3% | #15 of 42 | Official leaderboard | |
| OpenAI MRCR | 57.2% | #4 of 10 | Model card | |
| FACTS Parametric | 51.5% | #19 of 45 | Official leaderboard | |
| IFEval | 87.4% | #54 of 126 | Model card | |
| Judgemark v2.1 | 76.3 | #18 of 42 | Official leaderboard | |
| FACTS Multimodal | 40.1% | #18 of 39 | Official leaderboard | |
| Phare | 67.1% | #29 of 62 | Official leaderboard | |
| Wer wird Millionär? LLM Benchmark | 7022.0 | #36 of 76 | Official leaderboard | |
| Arena-Hard v2.0 | 50% | #11 of 23 | Official leaderboard | |
| Fiction.LiveBench | 63.9% | #29 of 57 | Epoch AI | |
| EQ-Bench 3 | 1,257 | #41 of 78 | Official leaderboard | |
| WritingBench | 70.9 | #25 of 45 | Official leaderboard | |
| Creative Writing v3 | 65.8 | #68 of 120 | Official leaderboard | |
| Global MMLU Lite | 87.5% | #25 of 43 | Official leaderboard | |
| FACTS Benchmark Suite | 40.1% | #26 of 40 | Official leaderboard | |
| FACTS Grounding | 74.5% | #23 of 34 | Official leaderboard | |
| IndicGenBench | 43.7 | #9 of 13 | Official leaderboard | |
| FACTS Search | 64.6% | #22 of 31 | Official leaderboard | |
| MultiNRC | 21.2% | #28 of 38 | Official leaderboard | |
| SimpleQA Verified | 31.1% | #63 of 84 | Epoch AI | |
| BullshitBench | 14.6% | #81 of 107 | Official leaderboard | |
| BullshitBench V2 | 14% | #98 of 122 | Official leaderboard | |
| GraphWalks | 61.7% | #17 of 21 | Model card | |
| Vectara Hallucination Leaderboard (HHEM) | 2.00% | #125 of 148 | Official leaderboard | |
| Humanity's Last Exam | 5.40% | #41 of 47 | Official leaderboard | |
| MultiChallenge | 39.4% | #34 of 35 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH Level 5 | 83% | #25 of 94 | Epoch AI | |
| ForecastBench | 62.1 | #36 of 86 | Official leaderboard | |
| CORE-Bench | 33.3% | #8 of 17 | Official leaderboard | |
| Misguided Attention | 44.2% | #23 of 45 | Official leaderboard | |
| GPQA Diamond | 66.9% | #114 of 219 | Epoch AI | |
| FrontierMath | 5.52% | #45 of 70 | Epoch AI | |
| OTIS Mock AIME 2024-2025 | 38.3% | #130 of 202 | Epoch AI | |
| DTBench | 47.1% | #115 of 178 | Official leaderboard | |
| PolyMath | 26.4% | #26 of 38 | Official leaderboard | |
| SimpleBench | 27% | #83 of 100 | Official leaderboard | |
| FrontierMath Tier 4 | 0% | #49 of 55 | Epoch AI | |
| PHYBench | 13.2% | #25 of 28 | Official leaderboard | |
| ARC-AGI-2 | 0.42% | #86 of 95 | Official leaderboard | |
| ARC-AGI | 5.50% | #86 of 92 | Official leaderboard | |
| AMO-Bench | 4.10% | #20 of 21 | Official leaderboard | |
| FrontierMath Tiers 1-3 v2 | 5.96% | #85 of 89 | Epoch AI | |
| Verifying the Verifiers (Project APE CRED benchmark) | 14% | #22 of 23 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench-Hard | 32.8% | #8 of 96 | Official leaderboard | |
| AutoCodeBench | 48% | #9 of 34 | Official leaderboard | |
| Aider Polyglot | 52.4% | #25 of 54 | Epoch AI | |
| SWE-bench Multimodal | 31.1% | #5 of 9 | Official leaderboard | |
| WeirdML | 39% | #82 of 112 | Official leaderboard | |
| ArtifactsBench | 46% | #15 of 20 | Official leaderboard | |
| ALE-Bench | 558 | #98 of 121 | Epoch AI | |
| SWE-bench-Live | 16.3% | #11 of 13 | Official leaderboard | |
| SWE-bench Verified | 48.5% | #31 of 32 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Galileo Agent Leaderboard v2 | 62% | #1 of 21 | Official leaderboard | |
| Berkeley Function Calling Leaderboard (BFCL) | 68.9% | #7 of 67 | Official leaderboard | |
| GAIA | 83.1% | #7 of 57 | Official leaderboard | |
| SnakeBench | 32 | #25 of 183 | Official leaderboard | |
| Galileo Agent Leaderboard | 0.92 | #5 of 31 | Official leaderboard | |
| BFCL V4 | 54% | #16 of 65 | Official leaderboard | |
| LiveResearchBench | 65.6 | #3 of 7 | Official leaderboard | |
| LLM Chess | -111 | #76 of 124 | Official leaderboard | |
| Pencil Puzzle Bench | 0% | #33 of 53 | Official leaderboard | |
| LisanBench | 172.0 | #96 of 133 | Official leaderboard | |
| MCP-Universe | 19.9% | #24 of 30 | Official leaderboard | |
| CompileBench | 60% | #17 of 20 | Official leaderboard | |
| MCPMark | 8.07% | #24 of 28 | Official leaderboard | |
| tau2-bench | 54.7% | #9 of 10 | Official leaderboard | |
| Chess Puzzles | 3.00% | #81 of 83 | Epoch AI | |
| UniClawBench | 15.3% | #10 of 10 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CaseLaw v2 | 69.9% | #3 of 53 | Official leaderboard | |
| TaxEval v2 | 75.1% | #24 of 129 | Official leaderboard | |
| LEXam | 57.5% | #6 of 31 | Official leaderboard | |
| CorpFin v2 | 63% | #47 of 119 | Official leaderboard | |
| MortgageTax | 65.9% | #35 of 86 | Official leaderboard | |
| LegalBench | 83.1% | #59 of 138 | Official leaderboard | |
| CadEval | 42% | #8 of 15 | Epoch AI | |
| ProfBench | 46.3% | #40 of 72 | Official leaderboard | |
| Vals Finance Agent v1 | 24.6% | #29 of 47 | Official leaderboard | |
| PRBench | 36.5% | #40 of 44 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| A-Bench | 79.6% | #2 of 116 | Official leaderboard | |
| MMBench-EN v1.1 | 86.9% | #7 of 178 | Official leaderboard | |
| MMBench | 86.9% | #9 of 155 | Official leaderboard | |
| MMStar | 69.8% | #11 of 173 | Official leaderboard | |
| CCBench (MMBench Chinese Culture) | 73.5% | #23 of 152 | Official leaderboard | |
| VHELM | 69.5 | #9 of 41 | Official leaderboard | |
| MMMU | 74.8% | #41 of 97 | Model card | |
| VISTA | 45.3% | #26 of 54 | Official leaderboard | |
| Vision Arena | 1,214 | #71 of 136 | Official leaderboard | |
| GeoBench | 72% | #26 of 48 | Official leaderboard | |
| MathVista | 72.2% | #37 of 64 | Model card | |
| Math-VR | 26% | #16 of 26 | Official leaderboard | |
| MADQA | 60% | #11 of 16 | Official leaderboard | |
| Point-Bench | 33.3% | #12 of 17 | Official leaderboard | |
| ZeroBench | 3.00% | #49 of 66 | Official leaderboard | |
| EnigmaEval | 2.17% | #32 of 41 | Epoch AI | |
| Video-MME | 72% | #35 of 42 | Model card | |
| CharXiv | 56.7% | #61 of 67 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SimpleSafetyTests | 100% | #10 of 75 | Official leaderboard | |
| HELM Safety | 96.3 | #17 of 75 | Official leaderboard | |
| BaxBench | 40.8% | #9 of 34 | Official leaderboard | |
| Anthropic Red Team | 99.3% | #28 of 75 | Official leaderboard | |
| AIR-Bench 2024 | 64.8% | #43 of 82 | Official leaderboard | |
| KORA | 26.2% | #29 of 42 | Official leaderboard | |
| FORTRESS | 53% | #54 of 66 | Official leaderboard | |
| CyberGym | 9.36% | #27 of 33 | Official leaderboard | |
| Human Pathogen Capabilities Test v2 (HPCT v2) | 34.2% | #60 of 71 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 75.9 | #9 of 173 | Official leaderboard | |
| HELM Capabilities | 72.7 | #16 of 60 | Official leaderboard | |
| ACCoRD | 56.0 | #101 of 150 | Official leaderboard | |
| LMCA | 25.6% | #94 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 36.0 | #106 of 149 | Official leaderboard |
OpenAI's models in color, against every other model on the Epoch Capabilities Index, by release date.
The benchmarks the lab chose to headline, with the scores it gave.