OpenAI · model
GPT-4.1 benchmark scores
As of 2026-11-22, GPT-4.1 (OpenAI) has measured scores on 21 benchmarks and estimated scores on 106 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 66.6% | measured |
| AA-HLE | 4.2% | measured |
| AA-SciCode | 35.8% | estimated ± 3.8 pp, high confidence |
| AIME26 | 78.4% | estimated ± 1.4 pp, medium confidence |
| Artificial Analysis Intelligence Index | 12.7% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 14.7% | estimated ± 10.5 pp, low confidence |
| GPQA Diamond | 66.6% | estimated ± 1.2 pp, high confidence |
| HLE | 7.2% | estimated ± 6.5 pp, medium confidence |
| IFBench | 54.5% | estimated ± 6.6 pp, medium confidence |
| AA-LCR | 68.3% | measured |
| AA-Omniscience Accuracy | 27.8% | measured |
| SciCode | 35.2% | estimated ± 3.6 pp, high confidence |
| BrowseComp | 63.6% | estimated ± 8.8 pp, low confidence |
| HLE w/ tools | 39.6% | estimated ± 5.7 pp, low confidence |
| IFEval | 87.4% | measured |
| LongBench v2 | 57.6% | estimated ± 5.5 pp, medium confidence |
| τ²-bench results | 47.1% | measured |
| AA Coding Index | 25.6% | estimated ± 5.3 pp, medium confidence |
| AA-MMMU-Pro | 61.2% | measured |
| APEX-Agents-AA | 8.5% | estimated ± 9.3 pp, low confidence |
| BioMysteryBench (human-difficult) | 0.0% | estimated ± 6.8 pp, low confidence |
| SWE-bench Verified | 54.6% | measured |
| BFCL v4 | 41.4% | estimated ± 8.5 pp, low confidence |
| CyberGym | 38.7% | estimated ± 11.0 pp, low confidence |
| JobBench | 13.3% | estimated ± 14.2 pp, low confidence |
| SWE-bench Pro | 30.4% | estimated ± 4.5 pp, high confidence |
| WideResearch | 60.4% | estimated ± 3.3 pp, medium confidence |
| AA Agentic Index | 11.3% | estimated ± 9.4 pp, low confidence |
| MMLU-Pro | 82.3% | estimated ± 4.0 pp, high confidence |
| AA-IFBench | 43.0% | measured |
| BBH | 95.9% | estimated ± 2.4 pp, low confidence |
| FailureSensorIQ | 64.1% | estimated ± 2.1 pp, high confidence |
| GPQA | 66.3% | measured |
| MMLU | 90.2% | measured |
| Vals GPQA Diamond | 65.4% | measured |
| Vals LiveCodeBench | 54.7% | measured |
| Vals MMLU-Pro | 80.5% | measured |
| MMMLU | 83.3% | estimated ± 0.7 pp, medium confidence |
| MMMU | 73.9% | estimated ± 2.7 pp, high confidence |
| Chess Puzzles | 11.0% | measured |
| AA MMLU-Pro | 85.3% | estimated ± 0.8 pp, high confidence |
| Gert Labs | 18.9% | measured |
| ApprenticeBench | 3.1% | estimated ± 10.4 pp, low confidence |
| ARC-AGI-1 | 33.4% | estimated ± 6.5 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 13.8 pp, low confidence |
| CursorBench 3.2 | 59.1% | estimated ± 7.2 pp, low confidence |
| EBR-bench | 4.1% | estimated ± 12.7 pp, low confidence |
| FrontierMath v2 (Tier 4) | 0.0% | estimated ± 4.0 pp, medium confidence |
| FrontierMath v2 (Tiers 1-3) | 6.0% | measured |
| Furniture Assembly | 25.1% | estimated ± 14.1 pp, low confidence |
| MaxxBench | 34.7% | estimated ± 10.3 pp, low confidence |
| MazeBench | 0.0% | estimated ± 2.7 pp, medium confidence |
| Mystery Game Puzzles | 6.4% | estimated ± 4.7 pp, medium confidence |
| NYT Connections | 44.6% | estimated ± 12.6 pp, low confidence |
| OSWorld-Verified | 60.3% | estimated ± 8.6 pp, low confidence |
| ParseBench-1 | 46.9% | estimated ± 6.2 pp, medium confidence |
| Vals SWE-bench | 42.0% | estimated ± 6.6 pp, low confidence |
| VulcanBench v3 | 76.5% | estimated ± 5.6 pp, low confidence |
| CWE-Bench-AA | 29.9% | estimated ± 8.1 pp, low confidence |
| AA Cyber Index | 2.3% | estimated ± 12.4 pp, low confidence |
| DeepsecBench-AA | 5.4% | estimated ± 8.2 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 49.7% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 46.5% | estimated ± 1.1 pp, low confidence |
| AA ITBench | 35.6% | estimated ± 4.6 pp, low confidence |
| CWE-bench v1 | 32.2% | estimated ± 5.7 pp, low confidence |
| FrontierPhysics | 0.0% | estimated ± 6.1 pp, low confidence |
| HLE w/o tools | 24.9% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.1 | 0.8% | estimated ± 3.6 pp, medium confidence |
| SpireClimb | 0.0% | estimated ± 10.3 pp, low confidence |
| StealthMark | 31.9% | estimated ± 9.7 pp, low confidence |
| Toolathlon-Verified | 53.3% | estimated ± 3.0 pp, high confidence |
| AA AutomationBench | 37.2% | estimated ± 9.9 pp, low confidence |
| GDP.pdf | 9.1% | estimated ± 4.2 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 8.6 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| CWE-bench | 24.7% | estimated ± 6.2 pp, low confidence |
| MKA | 32.7% | estimated ± 4.6 pp, medium confidence |
| SkillsBench official leaderboard (BenchFlow) | 40.1% | estimated ± 6.2 pp, medium confidence |
| CompileBench | 53.3% | measured |
| Vibe Code Bench | 0.0% | estimated ± 8.4 pp, low confidence |
| FACTS Multimodal | 32.9% | estimated ± 5.6 pp, low confidence |
| Hermes Index | 13.7% | estimated ± 5.7 pp, low confidence |
| ParseBench-2 | 47.5% | estimated ± 6.2 pp, medium confidence |
| CharXiv | 71.3% | estimated ± 6.3 pp, low confidence |
| ExploitBench | 10.6% | estimated ± 13.4 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 8.3 pp, low confidence |
| AI2D_TEST | 88.0% | estimated ± 2.0 pp, medium confidence |
| C-Eval | 89.4% | estimated ± 1.0 pp, medium confidence |
| ERQA | 41.2% | estimated ± 3.1 pp, medium confidence |
| HMMT Feb 2026 | 78.4% | estimated ± 3.1 pp, medium confidence |
| HMMT Nov 2025 | 73.1% | estimated ± 1.5 pp, low confidence |
| MathVision | 59.2% | estimated ± 3.1 pp, medium confidence |
| MMAnswerBench | 75.3% | estimated ± 2.4 pp, low confidence |
| MMLU-ProX | 72.7% | measured |
| MMLU-Redux | 94.5% | estimated ± 0.8 pp, medium confidence |
| MMMU-Pro | 62.4% | estimated ± 1.5 pp, high confidence |
| NL2Repo | 7.2% | estimated ± 6.2 pp, low confidence |
| ScreenSpot Pro | 65.2% | estimated ± 10.8 pp, low confidence |
| SuperGPQA | 46.0% | estimated ± 8.5 pp, low confidence |
| Toolathlon | 37.8% | estimated ± 8.0 pp, low confidence |
| Video-MME (w/o subtitle) | 75.1% | estimated ± 1.7 pp, medium confidence |
| HealthBench Hard | 0.0% | estimated ± 8.6 pp, low confidence |
| MedXpertQA (MM) | 5.0% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 68.2% | estimated ± 2.7 pp, low confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, low confidence |
| DAYJOB | 0.4% | estimated ± 6.3 pp, low confidence |
| DAYJOB Healthcare | 0.1% | estimated ± 6.1 pp, low confidence |
| Finance Agent v2 | 55.1% | estimated ± 2.4 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (length-adjusted) | 54.1% | estimated ± 3.7 pp, medium confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| HLE-Verified | 22.4% | estimated ± 7.1 pp, low confidence |
| BlenderWorld (text-only) | 70.6% | estimated ± 4.0 pp, low confidence |
| Cookie-Bench | 74.3% | estimated ± 2.5 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 28.8% | estimated ± 4.3 pp, medium confidence |
| LiveCodeBench | 61.9% | estimated ± 14.6 pp, low confidence |
| Agents' Last Exam | 29.6% | estimated ± 9.7 pp, low confidence |
| SEC-Bench Pro | 18.0% | estimated ± 12.3 pp, low confidence |
| MRCRv2 | 65.9% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 60.8% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 34.1% | estimated ± 3.8 pp, low confidence |
| LifeVal | 0.5% | estimated ± 5.0 pp, low confidence |
| MMMU-Pro w/ Python | 65.8% | estimated ± 2.0 pp, medium confidence |
| ExploitBench Internal Port | 0.0% | estimated ± 1.4 pp, low confidence |