MiniMax · model
MiniMax M2.7 benchmark scores
As of 2026-10-07, MiniMax M2.7 (MiniMax) has measured scores on 30 benchmarks and estimated scores on 75 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 87.4% | measured |
| AA-HLE | 29.6% | measured |
| AA-SciCode | 50.1% | measured |
| Artificial Analysis Intelligence Index | 22.8% | measured |
| CritPt | 0.6% | measured |
| GDPval-AA | 25.7% | measured |
| GPQA Diamond | 87.0% | measured |
| HLE | 33.3% | estimated ± 9.2 pp, medium confidence |
| IFBench | 74.3% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 78.3% | measured |
| LiveCodeBench v6 | 87.9% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 26.8% | measured |
| SciCode | 36.6% | estimated ± 2.9 pp, low confidence |
| Terminal-Bench 2.1 | 59.1% | estimated ± 6.9 pp, medium confidence |
| BrowseComp | 55.2% | estimated ± 3.4 pp, medium confidence |
| HLE w/ tools | 44.8% | estimated ± 6.1 pp, low confidence |
| IFEval | 93.7% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| VITA-Bench | 28.2% | estimated ± 10.7 pp, low confidence |
| τ²-bench results | 84.8% | measured |
| AA Coding Index | 52.6% | measured |
| APEX-Agents | 23.5% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 10.6% | measured |
| BioMysteryBench (human-difficult) | 32.7% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 81.8% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 77.4% | estimated ± 2.4 pp, high confidence |
| AutomationBench | 28.4% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 74.2% | estimated ± 2.6 pp, high confidence |
| CyberGym | 58.5% | estimated ± 5.3 pp, low confidence |
| JobBench | 34.1% | estimated ± 7.3 pp, low confidence |
| SWE-bench Pro | 56.2% | measured |
| τ³-bench results | 70.3% | estimated ± 2.1 pp, low confidence |
| WideResearch | 78.2% | estimated ± 5.6 pp, low confidence |
| AA Agentic Index | 16.8% | measured |
| MMLU-Pro | 85.6% | estimated ± 3.5 pp, high confidence |
| GPQA | 87.0% | estimated ± 0.1 pp, high confidence |
| AA-IFBench | 75.7% | measured |
| Gert Labs | 40.4% | measured |
| AA-AnalystAgent | 18.0% | estimated ± 12.0 pp, low confidence |
| AA EnterpriseOps-Gym | 29.5% | estimated ± 3.6 pp, medium confidence |
| AA Harvey LAB | 80.0% | estimated ± 1.2 pp, low confidence |
| ApprenticeBench | 0.0% | estimated ± 3.1 pp, low confidence |
| ARC-AGI-1 | 84.2% | estimated ± 2.7 pp, medium confidence |
| ARC-AGI-2 | 45.2% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 44.3% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 52.5% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 1.7% | estimated ± 6.9 pp, low confidence |
| FrontierCode 1.1 Main | 23.1% | estimated ± 3.8 pp, medium confidence |
| FrontierSWE v2 | 8.4% | estimated ± 9.0 pp, medium confidence |
| OSWorld-Verified | 54.5% | estimated ± 5.9 pp, medium confidence |
| Vals GPQA Diamond | 86.6% | measured |
| Vals LiveCodeBench | 79.9% | measured |
| Vals MMLU-Pro | 80.4% | measured |
| Vals SWE-bench | 73.8% | measured |
| Terminal-Bench 2.1 (Vals AI) | 48.7% | measured |
| VulcanBench v3 | 80.9% | estimated ± 5.6 pp, low confidence |
| AA AutomationBench | 4.3% | estimated ± 7.0 pp, medium confidence |
| GDP.pdf | 9.4% | estimated ± 5.4 pp, medium confidence |
| AA ITBench | 53.3% | estimated ± 3.6 pp, low confidence |
| AA Tau3 Banking | 22.0% | estimated ± 5.8 pp, medium confidence |
| AA Terminal-Bench 2.1 | 55.1% | estimated ± 4.4 pp, high confidence |
| AA Terminal-Bench 4.0 | 0.9% | estimated ± 14.0 pp, low confidence |
| CursorBench 4.0 | 17.6% | estimated ± 1.6 pp, medium confidence |
| CWE-bench v1 | 35.6% | estimated ± 6.9 pp, low confidence |
| DeepSWE | 18.3% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 26.3% | estimated ± 4.4 pp, high confidence |
| OSWorld 2.0 | 0.0% | estimated ± 4.5 pp, low confidence |
| PostTrainBench v1.1 | 22.8% | estimated ± 2.7 pp, high confidence |
| SWE Multilingual | 76.5% | measured |
| Toolathlon-Verified | 43.3% | estimated ± 2.3 pp, low confidence |
| Vibe Code Bench | 27.0% | measured |
| ExploitGym | 0.0% | estimated ± 12.2 pp, low confidence |
| C-Eval | 92.2% | estimated ± 1.0 pp, medium confidence |
| Claw-Eval | 48.7% | measured |
| MCP Atlas | 64.6% | estimated ± 7.8 pp, low confidence |
| MCP-Tasks | 54.0% | estimated ± 6.4 pp, low confidence |
| MMLU-ProX | 85.3% | estimated ± 1.7 pp, medium confidence |
| MMLU-Redux | 94.9% | estimated ± 1.1 pp, medium confidence |
| NL2Repo | 39.8% | measured |
| NOVA-63 | 57.8% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| SuperGPQA | 71.8% | estimated ± 7.5 pp, medium confidence |
| Terminal-Bench 2.0 | 57.0% | measured |
| Toolathlon | 46.3% | measured |
| HealthBench Hard | 13.1% | estimated ± 7.7 pp, low confidence |
| LiveCodeBench Pro | 80.7% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 45.9% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 80.8% | measured |
| React Native Evals | 71.4% | measured |
| ResearchClawBench | 13.5% | estimated ± 1.3 pp, medium confidence |
| SWE-Rebench | 51.9% | measured |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| DRACO | 72.1% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 20.7% | estimated ± 2.4 pp, low confidence |
| HealthBench (raw) | 38.8% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 49.8% | estimated ± 1.3 pp, low confidence |
| HealthBench Professional (raw) | 49.9% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 77.7% | estimated ± 1.8 pp, low confidence |
| LiveCodeBench | 100.0% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 54.5% | estimated ± 2.4 pp, high confidence |
| MMMLU | 88.6% | estimated ± 1.1 pp, medium confidence |
| MMLU | 89.7% | estimated ± 1.1 pp, medium confidence |