gpt-oss-120b ranks first on AIME 2024.
Open weights Mid-size
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 | |
|---|---|---|---|---|
| MMLU | 90% | #15 of 127 | Model card | |
| MMLU-Pro | 80.8% | #54 of 212 | Official leaderboard | |
| SuperGPQA | 51.9% | #19 of 58 | Official leaderboard | |
| LLM Confabulation Leaderboard | 15.7% | #25 of 58 | Official leaderboard | |
| Lech Mazur Creative Writing | 7.71 | #22 of 44 | Epoch AI | |
| Phare | 66.1% | #32 of 62 | Official leaderboard | |
| LMArena (Elo) | 1,352 | #175 of 333 | Official leaderboard | |
| Wer wird Millionär? LLM Benchmark | 3111.0 | #40 of 76 | Official leaderboard | |
| MMMLU | 81.3% | #38 of 62 | Model card | |
| SEA-HELM | 66.1 | #38 of 62 | Official leaderboard | |
| Humanity's Last Exam | 19% | #101 of 147 | Model card | |
| SimpleQA | 16.8% | #41 of 59 | Model card | |
| EQ-Bench 3 | 1,073 | #58 of 78 | Official leaderboard | |
| PersonQA | 29.8% | #7 of 9 | Model card | |
| SimpleQA Verified | 13.1% | #44 of 56 | Official leaderboard | |
| Vectara Hallucination Leaderboard (HHEM) | 2.40% | #120 of 148 | Official leaderboard | |
| SimpleQA Hallucination Rate | 78.2% | #10 of 12 | Model card | |
| Fiction.LiveBench | 44.4% | #48 of 57 | Epoch AI | |
| BullshitBench V2 | 12% | #103 of 122 | Official leaderboard | |
| FACTS Parametric | 10.7% | #38 of 45 | Official leaderboard | |
| IndicGenBench | 39.1 | #11 of 13 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 14.2% | #90 of 104 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 35.8 | #104 of 119 | Official leaderboard | |
| Judgemark v2.1 | 54.8 | #37 of 42 | Official leaderboard | |
| MultiChallenge | 45.3% | #31 of 35 | Official leaderboard | |
| MultiNRC | 15.2% | #34 of 38 | Official leaderboard | |
| SkateBench v2 | 16.4% | #19 of 21 | Official leaderboard | |
| Creative Writing v3 | 47.9 | #111 of 120 | Official leaderboard | |
| FACTS Search | 44.5% | #29 of 31 | Official leaderboard | |
| BullshitBench | 3.64% | #106 of 107 | Official leaderboard | |
| Judgemark v4 | 15.5 | #40 of 40 | Official leaderboard | |
| FACTS Grounding v2 | 20.1% | #15 of 15 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2024 | 96.6% | #1 of 87 | Model card | |
| AIME 2025 | 97.9% | #15 of 143 | Model card | |
| HiPhO | 62.2% | #9 of 35 | Official leaderboard | |
| HMMT 2025 | 90% | #14 of 53 | Official leaderboard | |
| OTIS Mock AIME 2024-2025 | 88.9% | #62 of 202 | Epoch AI | |
| SMT 2025 | 87.7% | #15 of 40 | Official leaderboard | |
| CMIMC 2025 | 85% | #13 of 33 | Official leaderboard | |
| BRUMO 2025 | 92.5% | #19 of 42 | Official leaderboard | |
| GPQA Diamond | 75.8% | #100 of 219 | Epoch AI | |
| HMMT Nov 2025 | 90% | #11 of 22 | Official leaderboard | |
| CritPt | 1.14% | #90 of 160 | Epoch AI | |
| DTBench | 60.5% | #101 of 178 | Official leaderboard | |
| MathArena (Apex, IMO, USAMO) | 1.04% | #38 of 47 | Official leaderboard | |
| CORE-Bench | 11.1% | #15 of 17 | Official leaderboard | |
| SimpleBench | 22.1% | #91 of 100 | Official leaderboard | |
| Surface Evolver Bench | 25% | #24 of 26 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Codeforces rating | 2,622 | #10 of 41 | Model card | |
| ArtifactsBench | 56.9% | #5 of 20 | Official leaderboard | |
| WeirdML | 48.2% | #50 of 112 | Official leaderboard | |
| METR Time Horizon | 42 min | #20 of 39 | Epoch AI | |
| Aider Polyglot | 41.8% | #32 of 54 | Epoch AI | |
| OpenAI PRs | 37% | #9 of 12 | Model card | |
| AlgoTune | 1.41× | #14 of 18 | Official leaderboard | |
| SWE-Bench Pro | 16.2% | #19 of 24 | Official leaderboard | |
| ALE-Bench | 576 | #96 of 121 | Epoch AI | |
| SWE-bench Verified | 26% | #50 of 60 | Official leaderboard | |
| PaperBench | 11% | #13 of 14 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| tau-bench | 67.8% | #7 of 23 | Model card | |
| SnakeBench | 26 | #64 of 183 | Official leaderboard | |
| LisanBench | 1143.7 | #53 of 133 | Official leaderboard | |
| MCP-Universe | 25.5% | #16 of 30 | Official leaderboard | |
| Elimination Game | 4 | #32 of 56 | Official leaderboard | |
| Step Race | 2 | #35 of 59 | Official leaderboard | |
| BalatroBench | 6.27 | #10 of 16 | Official leaderboard | |
| Meta Agents Research Environments (ARE) / Gaia2 | 13.7% | #9 of 13 | Official leaderboard | |
| Agent Poker Bench | 1,015 | #13 of 17 | Official leaderboard | |
| PACT | 1,496 | #20 of 26 | Official leaderboard | |
| LLM Chess | -217 | #97 of 124 | Official leaderboard | |
| PinchBench | 59.7% | #40 of 48 | Official leaderboard | |
| Terminal-Bench | 18.7% | #15 of 18 | Epoch AI | |
| PinchBench 2.0 | 44.8% | #50 of 57 | Official leaderboard | |
| MCPMark | 4.72% | #26 of 28 | Official leaderboard | |
| Terminal-Bench 2.0 | 18.7% | #40 of 43 | Official leaderboard | |
| CivBench | 1,422 | #17 of 18 | Official leaderboard | |
| CompileBench | 60% | #19 of 20 | Official leaderboard | |
| Mystery Game Puzzles | 2.00% | #80 of 80 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ProfBench | 50% | #29 of 72 | Official leaderboard | |
| LEXam | 51.7% | #13 of 31 | Official leaderboard | |
| Vals Finance Agent v1 | 28.3% | #26 of 47 | Official leaderboard | |
| TaxEval v2 | 71.6% | #73 of 129 | Official leaderboard | |
| CorpFin v2 | 58.2% | #79 of 119 | Official leaderboard | |
| HealthBench | 57.6% | #20 of 30 | Model card | |
| PRBench | 40.2% | #33 of 44 | Official leaderboard | |
| LegalBench | 75.9% | #104 of 138 | Official leaderboard | |
| FailureSensorIQ | 50.5% | #20 of 24 | Official leaderboard | |
| Physical-Engineering's Last Exam | 0.05 | #15 of 18 | Official leaderboard | |
| HealthBench Hard | 30% | #18 of 21 | Model card | |
| Vals Finance Agent | 21.5% | #44 of 49 | Official leaderboard | |
| StockBench | -0.90% | #12 of 13 | Official leaderboard | |
| HealthBench Consensus | 89.9% | #16 of 17 | Model card | |
| CaseLaw v2 | 48.8% | #50 of 53 | Official leaderboard | |
| Vending-Bench 2 | $-22 | #64 of 66 | Official leaderboard | |
| APEX-Agents | 4.40% | #56 of 56 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| FORTRESS | 8.24% | #2 of 66 | Official leaderboard | |
| HELM Safety | 98.1 | #3 of 75 | Official leaderboard | |
| AIR-Bench 2024 | 88% | #5 of 82 | Official leaderboard | |
| Spiral-Bench v1.0 | 81.4 | #3 of 13 | Official leaderboard | |
| Spiral-Bench v1.2 | 57.5 | #5 of 21 | Official leaderboard | |
| SimpleSafetyTests | 100% | #18 of 75 | Official leaderboard | |
| Anthropic Red Team | 99.5% | #21 of 75 | Official leaderboard | |
| Tacit Knowledge and Troubleshooting | 74% | #10 of 29 | Model card | |
| Multimodal Troubleshooting Virology | 55% | #10 of 26 | Model card | |
| Capture the Flag (Collegiate) | 33% | #5 of 13 | Model card | |
| Agentic BAIM-LLM Evaluation (ABLE) | 51.7% | #8 of 16 | Official leaderboard | |
| Human Pathogen Capabilities Test v2 (HPCT v2) | 44.6% | #50 of 71 | Official leaderboard | |
| Capture the Flag (Professional) | 14% | #15 of 21 | Model card | |
| KORA | 22.6% | #35 of 42 | Official leaderboard | |
| ProtocolQA Open-Ended | 27% | #21 of 25 | Model card | |
| DistressBench | 63.7% | #36 of 42 | Official leaderboard | |
| TroubleshootingBench | 25% | #17 of 19 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Capabilities | 77.0 | #9 of 60 | Official leaderboard | |
| ACCoRD | 67.5 | #58 of 150 | Official leaderboard | |
| Conceptual Reasoning Index | 38.9 | #100 of 149 | Official leaderboard | |
| LMCA | 22.1% | #102 of 139 | Epoch AI |
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.
Every result in the longer documents the lab published with it. 21 of them aren't in the launch post.