OpenAI · model
GPT-5.2 benchmark scores
As of 2026-10-07, GPT-5.2 (OpenAI) has measured scores on 24 benchmarks and estimated scores on 91 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 90.3% | measured |
| AA-HLE | 37.7% | measured |
| AA-SciCode | 48.1% | estimated ± 3.8 pp, high confidence |
| AIME26 | 100.0% | estimated ± 0.6 pp, low confidence |
| Artificial Analysis Intelligence Index | 30.5% | measured |
| CritPt | 11.6% | measured |
| GDPval-AA | 37.3% | estimated ± 6.2 pp, medium confidence |
| GPQA Diamond | 92.4% | estimated ± 0.4 pp, high confidence |
| HLE | 44.8% | estimated ± 6.3 pp, medium confidence |
| IFBench | 74.0% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 82.7% | measured |
| LiveCodeBench v6 | 87.1% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 44.3% | measured |
| SciCode | 48.5% | estimated ± 3.8 pp, high confidence |
| BrowseComp | 65.8% | measured |
| HLE w/ tools | 35.2% | estimated ± 4.6 pp, high confidence |
| IFEval | 93.7% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, low confidence |
| VITA-Bench | 38.4% | estimated ± 9.9 pp, low confidence |
| τ²-bench results | 84.8% | measured |
| AA Coding Index | 60.2% | estimated ± 5.1 pp, medium confidence |
| AA-MMMU-Pro | 77.6% | estimated ± 4.9 pp, medium confidence |
| APEX-Agents-AA | 31.9% | estimated ± 3.6 pp, medium confidence |
| BioMysteryBench (human-difficult) | 43.1% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 78.6% | estimated ± 8.1 pp, low confidence |
| SWE-bench Verified | 80.0% | measured |
| AutomationBench | 19.8% | estimated ± 10.3 pp, low confidence |
| BFCL v4 | 60.5% | estimated ± 9.8 pp, low confidence |
| CyberGym | 68.1% | estimated ± 4.6 pp, medium confidence |
| JobBench | 34.3% | measured |
| SWE-bench Pro | 55.6% | measured |
| τ³-bench results | 68.9% | estimated ± 8.9 pp, medium confidence |
| WideResearch | 77.8% | estimated ± 1.2 pp, medium confidence |
| AA Agentic Index | 14.0% | estimated ± 6.4 pp, medium confidence |
| MMLU-Pro | 86.9% | estimated ± 3.0 pp, high confidence |
| FrontierMath v2 (Tier 4) | 18.8% | measured |
| FrontierMath v2 (Tiers 1-3) | 40.7% | measured |
| GPQA | 92.4% | measured |
| AA-IFBench | 75.4% | measured |
| Gert Labs | 46.5% | measured |
| AA-AnalystAgent | 12.0% | estimated ± 12.5 pp, low confidence |
| AA EnterpriseOps-Gym | 29.5% | estimated ± 3.6 pp, medium confidence |
| AA Harvey LAB | 86.9% | estimated ± 9.8 pp, low confidence |
| ApprenticeBench | 0.0% | estimated ± 3.1 pp, low confidence |
| ARC-AGI-1 | 86.2% | measured |
| ARC-AGI-2 | 52.9% | measured |
| CursorBench 3.1 | 51.7% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 51.4% | estimated ± 3.6 pp, high confidence |
| FrontierCode 1.1 Main | 25.1% | estimated ± 2.7 pp, medium confidence |
| FrontierSWE v2 | 7.3% | estimated ± 9.0 pp, medium confidence |
| OSWorld-Verified | 47.3% | measured |
| Vals GPQA Diamond | 90.0% | estimated ± 2.2 pp, high confidence |
| Vals LiveCodeBench | 82.5% | estimated ± 4.7 pp, medium confidence |
| Vals MMLU-Pro | 88.0% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 80.2% | estimated ± 6.3 pp, medium confidence |
| AA AutomationBench | 49.2% | estimated ± 5.0 pp, medium confidence |
| GDP.pdf | 17.8% | estimated ± 5.2 pp, low confidence |
| AA ITBench | 53.3% | estimated ± 3.6 pp, low confidence |
| AA Tau3 Banking | 19.2% | estimated ± 10.2 pp, low confidence |
| CursorBench 4.0 | 32.1% | estimated ± 3.6 pp, medium confidence |
| HLE w/o tools | 41.9% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.0 | 0.0% | estimated ± 3.6 pp, medium confidence |
| PostTrainBench v1.1 | 23.0% | estimated ± 4.7 pp, medium confidence |
| Toolathlon-Verified | 73.2% | estimated ± 1.3 pp, low confidence |
| Vibe Code Bench | 53.5% | measured |
| CharXiv | 82.1% | measured |
| CharXiv w/o tools | 83.7% | estimated ± 1.7 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 6.1 pp, low confidence |
| C-Eval | 94.5% | estimated ± 0.9 pp, low confidence |
| Claw-Eval | 66.0% | estimated ± 5.6 pp, low confidence |
| HMMT Nov 2025 | 93.2% | estimated ± 2.6 pp, low confidence |
| MathVision | 83.0% | measured |
| MCP Atlas | 59.1% | estimated ± 8.2 pp, medium confidence |
| MCP-Tasks | 72.8% | estimated ± 8.2 pp, low confidence |
| MMAnswerBench | 86.2% | estimated ± 1.3 pp, low confidence |
| MMLU-Redux | 97.0% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro | 79.5% | measured |
| NL2Repo | 47.3% | estimated ± 6.1 pp, medium confidence |
| ScreenSpot Pro | 61.6% | estimated ± 4.5 pp, medium confidence |
| SuperGPQA | 83.3% | estimated ± 7.5 pp, medium confidence |
| Toolathlon | 38.6% | estimated ± 3.5 pp, high confidence |
| V* | 75.9% | measured |
| VideoMMMU | 86.0% | estimated ± 1.0 pp, high confidence |
| ERQA | 59.1% | estimated ± 2.4 pp, low confidence |
| HealthBench Hard | 32.1% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 80.2% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 73.5% | estimated ± 2.4 pp, high confidence |
| MMLU-Pro (Arcee) | 100.0% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 82.2% | estimated ± 3.0 pp, medium confidence |
| ResearchClawBench | 15.6% | estimated ± 2.2 pp, medium confidence |
| SWE-Rebench | 61.8% | estimated ± 3.6 pp, medium confidence |
| ARC-AGI-3 | 0.1% | estimated ± 2.1 pp, high confidence |
| FrontierMath (legacy) | 41.3% | estimated ± 0.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 84.7% | estimated ± 0.6 pp, low confidence |
| FrontierCode 1.1 Extended | 54.5% | estimated ± 3.0 pp, low confidence |
| HealthBench (raw) | 46.9% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.6% | estimated ± 2.5 pp, low confidence |
| HealthBench Professional | 55.1% | estimated ± 4.6 pp, medium confidence |
| HealthBench Professional (raw) | 57.4% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 35.3% | estimated ± 0.7 pp, low confidence |
| LABBench2 | 64.1% | estimated ± 1.3 pp, low confidence |
| MMMU | 85.3% | estimated ± 1.1 pp, low confidence |
| LiveCodeBench | 86.5% | estimated ± 10.2 pp, low confidence |
| Agents' Last Exam | 48.9% | estimated ± 8.7 pp, low confidence |
| OpenHarmony Bench | 53.3% | estimated ± 4.9 pp, low confidence |
| BabyVision | 33.5% | estimated ± 4.3 pp, low confidence |
| MMVU | 73.9% | estimated ± 2.9 pp, low confidence |
| SimpleVQA | 67.7% | estimated ± 7.8 pp, low confidence |
| ZeroBench | 11.0% | estimated ± 4.7 pp, low confidence |
| MMLU | 94.1% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro w/ Python | 80.8% | estimated ± 0.6 pp, high confidence |
| MathVision w/ Python | 91.1% | estimated ± 0.5 pp, low confidence |
| RealWorldQA | 0.0% | estimated ± 0.8 pp, low confidence |
| Video-MME (with subtitle) | 87.8% | estimated ± 0.9 pp, medium confidence |
| OmniDocBench 1.5 | 91.7% | estimated ± 5.9 pp, low confidence |