GPT-5.4 Nano ranks first on Vectara Hallucination Leaderboard (2025 dataset).
Closed weights
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 | |
|---|---|---|---|---|
| Vectara Hallucination Leaderboard (2025 dataset) | 3.10% | #1 of 104 | Official leaderboard | |
| Wer wird Millionär? LLM Benchmark | 27733.0 | #26 of 76 | Official leaderboard | |
| LMArena (Elo) | 1,401 | #128 of 333 | Official leaderboard | |
| Humanity's Last Exam | 37.7% | #62 of 147 | Model card | |
| Longform Creative Writing (EQ-Bench) | 57.8 | #70 of 119 | Official leaderboard | |
| GraphWalks | 73.4% | #13 of 21 | Model card | |
| Judgemark v2.1 | 64.5 | #27 of 42 | Official leaderboard | |
| HELM Arabic Enterprise | 63.2 | #15 of 23 | Official leaderboard | |
| BullshitBench | 16.4% | #79 of 107 | Official leaderboard | |
| BullshitBench V2 | 14% | #99 of 122 | Official leaderboard | |
| OpenAI MRCR v2 | 44.2% | #8 of 9 | Model card | |
| HELM Arabic | 68.2 | #25 of 28 | Official leaderboard | |
| Judgemark v4 | 27.5 | #37 of 40 | Official leaderboard | |
| SimpleQA Verified | 11.7% | #81 of 84 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ForecastBench | 58.6 | #19 of 86 | Official leaderboard | |
| OTIS Mock AIME 2024-2025 | 87.8% | #68 of 202 | Epoch AI | |
| FrontierMath | 25.9% | #24 of 70 | Epoch AI | |
| CritPt | 9.25% | #60 of 160 | Epoch AI | |
| GPQA Diamond | 78.5% | #92 of 219 | Epoch AI | |
| FrontierMath Tier 4 | 6.25% | #25 of 55 | Epoch AI | |
| DTBench | 67.1% | #89 of 178 | Official leaderboard | |
| FrontierMath Tiers 1-3 v2 | 44.9% | #59 of 89 | Epoch AI | |
| ARC-AGI-2 | 5.69% | #63 of 95 | Official leaderboard | |
| ARC-AGI | 51.5% | #64 of 92 | Official leaderboard | |
| BixBench3 | 27.5 | #16 of 20 | Official leaderboard | |
| FrontierMath Tier 4 v2 | 12.2% | #58 of 71 | Epoch AI | |
| ProofBench | 5.00% | #51 of 59 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WeirdML | 49.2% | #48 of 112 | Official leaderboard | |
| ALE-Bench | 1,005 | #54 of 121 | Epoch AI | |
| IOI (Vals) | 15.3% | #29 of 55 | Official leaderboard | |
| Vibe Code Bench | 26.1% | #75 of 115 | Official leaderboard | |
| Code Migration | 14.5% | #56 of 78 | Official leaderboard | |
| StructEval | 69.8% | #21 of 28 | Official leaderboard | |
| SWE-Bench Pro | 52.4% | #58 of 77 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| tau2-bench | 92.5% | #10 of 69 | Model card | |
| Chess Puzzles | 45% | #27 of 83 | Epoch AI | |
| LisanBench | 1426.0 | #49 of 133 | Official leaderboard | |
| LLM Chess | 207 | #52 of 124 | Official leaderboard | |
| PinchBench | 69.5% | #23 of 48 | Official leaderboard | |
| Toolathlon | 35.5% | #28 of 50 | Official leaderboard | |
| PinchBench 2.0 | 69% | #34 of 57 | Official leaderboard | |
| Terminal-Bench 2.0 | 46.3% | #44 of 61 | Model card | |
| Mystery Game Puzzles | 9.00% | #69 of 80 | Epoch AI | |
| MCP Atlas | 56.1% | #37 of 40 | Model card | |
| SnakeBench | 13 | #172 of 183 | Official leaderboard | |
| OSWorld-Verified | 39% | #36 of 37 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CorpFin v2 | 61.2% | #57 of 119 | Official leaderboard | |
| MedCode | 41% | #56 of 96 | Official leaderboard | |
| Vals Finance Agent | 47.8% | #30 of 49 | Official leaderboard | |
| MedScribe | 77.1% | #65 of 98 | Official leaderboard | |
| LegalBench | 77.9% | #97 of 138 | Official leaderboard | |
| MortgageTax | 59.1% | #64 of 86 | Official leaderboard | |
| TaxEval v2 | 67.4% | #98 of 129 | Official leaderboard | |
| Excel Modeling Benchmark | 44.8% | #59 of 76 | Official leaderboard | |
| Vals Finance Agent v2 | 38.2% | #64 of 80 | Official leaderboard | |
| CaseLaw v2 | 51.9% | #46 of 53 | Official leaderboard | |
| Harvey LAB (Legal Agent Benchmark) | 0% | #71 of 80 | Official leaderboard | |
| Legal Research Bench | 6.25% | #82 of 88 | Official leaderboard | |
| Tax Agent Bench | 4.97% | #75 of 79 | Official leaderboard | |
| PolicyBench | 65.3% | #50 of 50 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OmniDocBench v1.5 | 0.24 | #7 of 13 | Model card | |
| MMMU-Pro | 69.5% | #42 of 72 | Model card | |
| Vision Arena | 1,199 | #81 of 136 | Official leaderboard | |
| ParseBench | 43.4% | #35 of 42 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BrowseSafe++ | 76.1% | #9 of 15 | Official leaderboard | |
| PCT (Polarized Contrastive Pairs) | 63.3% | #46 of 46 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ACCoRD | 67.3 | #59 of 150 | Official leaderboard | |
| LMCA | 36.9% | #66 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 49.0 | #71 of 149 | Official leaderboard | |
| CAIS Risk Index | 56.8 | #43 of 65 | Official leaderboard | |
| SAGE (Vals) | 38.1% | #61 of 81 | Official leaderboard | |
| CAIS Text Capabilities Index | 16.1 | #56 of 66 | Official leaderboard | |
| Vals Multimodal Index | 47.6% | #28 of 33 | Official leaderboard | |
| CAIS Vision Capabilities Index | 38.9 | #45 of 53 | 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.