OpenAI · model
GPT-5.6 Terra benchmark scores
As of 2026-10-07, GPT-5.6 Terra (OpenAI) has measured scores on 49 benchmarks and estimated scores on 79 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 92.5% | measured |
| AA-HLE | 42.9% | measured |
| AA-SciCode | 55.0% | measured |
| AIME26 | 100.0% | estimated ± 0.6 pp, low confidence |
| Artificial Analysis Intelligence Index | 54.9% | measured |
| CritPt | 30.0% | measured |
| GDPval-AA | 47.7% | measured |
| GPQA Diamond | 92.9% | measured |
| HLE | 58.6% | estimated ± 5.5 pp, low confidence |
| IFBench | 69.7% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 83.0% | measured |
| LiveCodeBench v6 | 91.1% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 46.8% | measured |
| SciCode | 48.5% | estimated ± 2.9 pp, medium confidence |
| Terminal-Bench 2.1 | 87.4% | measured |
| BrowseComp | 87.5% | measured |
| HLE w/ tools | 58.7% | estimated ± 4.6 pp, high confidence |
| IFEval | 93.5% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, low confidence |
| VITA-Bench | 46.0% | estimated ± 9.9 pp, low confidence |
| τ²-bench results | 86.3% | measured |
| AA Coding Index | 76.7% | measured |
| AA-MMMU-Pro | 80.7% | measured |
| APEX-Agents | 39.6% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 38.9% | measured |
| BioMysteryBench (human-difficult) | 44.2% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 92.4% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 84.9% | estimated ± 2.5 pp, high confidence |
| AutomationBench | 28.7% | estimated ± 5.8 pp, medium confidence |
| BFCL v4 | 77.3% | estimated ± 2.6 pp, medium confidence |
| CyberGym | 81.8% | measured |
| JobBench | 63.3% | estimated ± 4.9 pp, medium confidence |
| SWE-bench Pro | 63.4% | measured |
| τ³-bench results | 71.8% | estimated ± 2.1 pp, low confidence |
| WideResearch | 81.0% | estimated ± 4.6 pp, high confidence |
| AA Agentic Index | 43.7% | measured |
| MMLU-Pro | 87.0% | estimated ± 3.0 pp, medium confidence |
| FrontierMath v2 (Tier 4) | 68.3% | measured |
| FrontierMath v2 (Tiers 1-3) | 84.9% | measured |
| GPQA | 92.9% | measured |
| AA-IFBench | 71.2% | measured |
| Gert Labs | 69.7% | estimated ± 3.0 pp, medium confidence |
| AA-AnalystAgent | 54.4% | estimated ± 5.5 pp, medium confidence |
| AA EnterpriseOps-Gym | 31.8% | estimated ± 3.6 pp, medium confidence |
| AA Harvey LAB | 92.9% | estimated ± 1.2 pp, medium confidence |
| ApprenticeBench | 16.0% | measured |
| ARC-AGI-1 | 96.5% | measured |
| ARC-AGI-2 | 83.9% | measured |
| CursorBench 3.1 | 56.3% | estimated ± 3.4 pp, medium confidence |
| CursorBench 3.2 | 64.9% | measured |
| Terminal-Bench 3.0 | 20.8% | measured |
| FrontierCode 1.1 Main | 47.9% | estimated ± 1.6 pp, medium confidence |
| FrontierSWE v2 | 27.1% | estimated ± 7.6 pp, medium confidence |
| OfficeQA Pro | 62.0% | estimated ± 7.2 pp, medium confidence |
| OSWorld-Verified | 78.0% | estimated ± 1.9 pp, medium confidence |
| Vals GPQA Diamond | 90.9% | measured |
| Vals LiveCodeBench | 85.9% | measured |
| Vals MMLU-Pro | 86.7% | measured |
| Vals SWE-bench | 95.4% | measured |
| Terminal-Bench 2.1 (Vals AI) | 77.5% | measured |
| VulcanBench v3 | 87.0% | measured |
| AA AutomationBench | 62.7% | estimated ± 5.5 pp, low confidence |
| GDP.pdf | 22.9% | estimated ± 4.4 pp, low confidence |
| AA ITBench | 51.0% | measured |
| AA Tau3 Banking | 45.6% | estimated ± 3.0 pp, low confidence |
| AA Terminal-Bench 2.1 | 84.9% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 27.8% | estimated ± 8.9 pp, medium confidence |
| CursorBench 4.0 | 41.3% | measured |
| CWE-bench v1 | 54.3% | estimated ± 6.9 pp, medium confidence |
| DeepSWE | 69.6% | measured |
| HLE w/o tools | 43.5% | estimated ± 4.4 pp, high confidence |
| OSWorld 2.0 | 50.2% | measured |
| PostTrainBench v1.1 | 34.4% | estimated ± 2.7 pp, high confidence |
| ProgramBench | 83.2% | estimated ± 6.0 pp, low confidence |
| Toolathlon-Verified | 78.7% | estimated ± 1.0 pp, medium confidence |
| Vibe Code Bench | 74.5% | estimated ± 10.3 pp, low confidence |
| CharXiv | 84.0% | estimated ± 5.4 pp, medium confidence |
| CharXiv w/o tools | 85.2% | estimated ± 1.8 pp, medium confidence |
| ExploitBench | 52.9% | measured |
| ExploitGym | 23.2% | measured |
| C-Eval | 94.7% | estimated ± 0.9 pp, low confidence |
| Claw-Eval | 81.7% | estimated ± 7.9 pp, low confidence |
| HMMT Nov 2025 | 93.2% | estimated ± 2.6 pp, low confidence |
| MathVision | 91.2% | estimated ± 3.6 pp, high confidence |
| MCP Atlas | 82.6% | estimated ± 3.5 pp, medium confidence |
| MCP-Tasks | 78.2% | estimated ± 7.0 pp, low confidence |
| MMAnswerBench | 97.4% | estimated ± 1.3 pp, low confidence |
| MMLU-Redux | 97.2% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro | 80.7% | measured |
| NL2Repo | 59.2% | estimated ± 4.7 pp, high confidence |
| QwenClawBench | 100.0% | estimated ± 6.0 pp, low confidence |
| ScreenSpot Pro | 79.5% | estimated ± 10.0 pp, low confidence |
| SuperGPQA | 84.4% | estimated ± 7.5 pp, low confidence |
| Terminal-Bench 2.0 | 78.3% | estimated ± 5.9 pp, low confidence |
| Toolathlon | 53.1% | measured |
| VideoMMMU | 87.3% | estimated ± 1.0 pp, high confidence |
| ERQA | 68.5% | estimated ± 3.9 pp, high confidence |
| HealthBench Hard | 32.7% | measured |
| LiveCodeBench Pro | 86.3% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 76.0% | estimated ± 2.4 pp, high confidence |
| MedXpertQA (Text) | 63.5% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 87.8% | estimated ± 3.4 pp, low confidence |
| React Native Evals | 100.0% | estimated ± 2.4 pp, low confidence |
| ResearchClawBench | 20.5% | estimated ± 2.0 pp, medium confidence |
| SWE-Rebench | 58.1% | estimated ± 8.9 pp, low confidence |
| ARC-AGI-3 | 0.8% | measured |
| FrontierMath (legacy) | 84.9% | measured |
| BioMysteryBench (human-solvable) | 89.5% | estimated ± 0.6 pp, medium confidence |
| DRACO | 81.1% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 55.8% | measured |
| HealthBench (raw) | 51.7% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.8% | estimated ± 0.9 pp, medium confidence |
| HealthBench Professional | 57.7% | measured |
| HealthBench Professional (raw) | 61.9% | estimated ± 5.0 pp, medium confidence |
| HLE-Verified | 51.1% | measured |
| LABBench2 | 81.2% | measured |
| MMMU | 87.9% | estimated ± 0.9 pp, medium confidence |
| LiveCodeBench | 100.0% | estimated ± 8.9 pp, low confidence |
| Agents' Last Exam | 24.2% | estimated ± 2.1 pp, high confidence |
| OpenHarmony Bench | 58.8% | estimated ± 2.4 pp, high confidence |
| SEC-Bench Pro | 67.0% | estimated ± 4.3 pp, medium confidence |
| SimpleVQA | 68.5% | estimated ± 8.2 pp, medium confidence |
| MMMLU | 90.8% | estimated ± 1.1 pp, low confidence |
| MMLU | 94.5% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro w/ Python | 82.0% | measured |
| RealWorldQA | 88.0% | estimated ± 1.2 pp, low confidence |
| Video-MME (with subtitle) | 88.8% | estimated ± 1.8 pp, medium confidence |
| OmniDocBench 1.5 | 91.7% | estimated ± 5.9 pp, low confidence |