Xiaomi · model
MiMo-V2-Pro benchmark scores
As of 2026-10-07, MiMo-V2-Pro (Xiaomi) has measured scores on 12 benchmarks and estimated scores on 58 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 87.0% | measured |
| AA-HLE | 30.4% | measured |
| AA-SciCode | 47.3% | estimated ± 3.9 pp, high confidence |
| Artificial Analysis Intelligence Index | 28.6% | measured |
| CritPt | 0.3% | measured |
| GDPval-AA | 29.9% | estimated ± 8.3 pp, low confidence |
| GPQA Diamond | 87.1% | estimated ± 2.2 pp, high confidence |
| HLE | 23.5% | estimated ± 9.5 pp, medium confidence |
| IFBench | 67.6% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 68.3% | measured |
| LiveCodeBench v6 | 86.0% | estimated ± 8.1 pp, low confidence |
| AA-Omniscience Accuracy | 26.6% | measured |
| SciCode | 47.6% | estimated ± 3.8 pp, high confidence |
| BrowseComp | 58.7% | estimated ± 5.7 pp, medium confidence |
| IFEval | 93.3% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| VITA-Bench | 35.6% | estimated ± 10.7 pp, low confidence |
| τ²-bench results | 95.0% | measured |
| AA Coding Index | 56.4% | estimated ± 5.1 pp, medium confidence |
| APEX-Agents-AA | 29.2% | estimated ± 10.0 pp, low confidence |
| BioMysteryBench (human-difficult) | 32.5% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 77.0% | estimated ± 10.2 pp, low confidence |
| SWE-bench Verified | 78.0% | measured |
| BFCL v4 | 49.6% | estimated ± 8.6 pp, low confidence |
| CyberGym | 28.0% | estimated ± 10.0 pp, low confidence |
| JobBench | 25.7% | estimated ± 8.4 pp, low confidence |
| SWE-bench Pro | 54.4% | estimated ± 3.2 pp, high confidence |
| τ³-bench results | 99.9% | estimated ± 8.9 pp, low confidence |
| WideResearch | 48.9% | estimated ± 5.9 pp, low confidence |
| AA Agentic Index | 17.7% | estimated ± 5.1 pp, medium confidence |
| MMLU-Pro | 85.6% | estimated ± 3.5 pp, high confidence |
| GPQA | 89.9% | estimated ± 3.2 pp, high confidence |
| AA-IFBench | 68.8% | measured |
| Gert Labs | 36.7% | measured |
| AA EnterpriseOps-Gym | 46.6% | estimated ± 3.6 pp, medium confidence |
| ApprenticeBench | 0.0% | estimated ± 3.1 pp, low confidence |
| ARC-AGI-1 | 83.9% | estimated ± 5.4 pp, medium confidence |
| ARC-AGI-2 | 47.1% | estimated ± 14.2 pp, low confidence |
| FrontierCode 1.1 Main | 18.6% | estimated ± 2.7 pp, low confidence |
| OSWorld-Verified | 53.3% | estimated ± 5.9 pp, medium confidence |
| Vals GPQA Diamond | 83.5% | estimated ± 7.4 pp, medium confidence |
| Vals LiveCodeBench | 80.1% | estimated ± 9.9 pp, low confidence |
| Vals MMLU-Pro | 84.3% | estimated ± 2.2 pp, high confidence |
| Vals SWE-bench | 73.6% | estimated ± 6.8 pp, medium confidence |
| AA ITBench | 45.6% | estimated ± 3.6 pp, medium confidence |
| HLE w/o tools | 27.5% | estimated ± 5.7 pp, medium confidence |
| OSWorld 2.0 | 0.0% | estimated ± 4.5 pp, low confidence |
| Vibe Code Bench | 23.1% | estimated ± 8.1 pp, medium confidence |
| C-Eval | 93.8% | estimated ± 1.0 pp, low confidence |
| Claw-Eval | 57.8% | measured |
| MCP Atlas | 47.3% | estimated ± 11.2 pp, low confidence |
| MCP-Tasks | 69.3% | estimated ± 6.4 pp, low confidence |
| MMLU-Redux | 94.9% | estimated ± 1.1 pp, medium confidence |
| NL2Repo | 43.2% | estimated ± 6.1 pp, medium confidence |
| SuperGPQA | 71.6% | estimated ± 7.5 pp, medium confidence |
| Toolathlon | 49.7% | estimated ± 6.9 pp, medium confidence |
| HealthBench Hard | 24.8% | estimated ± 7.7 pp, low confidence |
| MMLU-Pro (Arcee) | 78.3% | estimated ± 4.0 pp, low confidence |
| ResearchClawBench | 15.3% | measured |
| SWE-Rebench | 61.3% | estimated ± 3.6 pp, medium confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 39.6% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 57.7% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 50.7% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 72.5% | estimated ± 1.8 pp, low confidence |
| LiveCodeBench | 85.2% | estimated ± 10.2 pp, low confidence |
| MMLU | 89.6% | estimated ± 1.1 pp, medium confidence |