Xiaomi · model
MiMo-V2-Omni benchmark scores
As of 2026-11-22, MiMo-V2-Omni (Xiaomi) has measured scores on 11 benchmarks and estimated scores on 82 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 82.8% | measured |
| AA-HLE | 22.1% | measured |
| AA-SciCode | 46.0% | estimated ± 3.8 pp, high confidence |
| Artificial Analysis Intelligence Index | 23.9% | measured |
| CritPt | 1.1% | measured |
| GDPval-AA | 24.5% | estimated ± 11.0 pp, low confidence |
| GPQA Diamond | 82.8% | estimated ± 2.4 pp, high confidence |
| HLE | 24.8% | estimated ± 8.5 pp, medium confidence |
| IFBench | 57.0% | estimated ± 6.6 pp, medium confidence |
| AA-LCR | 75.0% | measured |
| AA-Omniscience Accuracy | 19.3% | measured |
| SciCode | 45.2% | estimated ± 3.6 pp, high confidence |
| BrowseComp | 71.4% | estimated ± 13.0 pp, low confidence |
| HLE w/ tools | 46.2% | estimated ± 5.5 pp, medium confidence |
| IFEval | 91.6% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 61.7% | estimated ± 5.5 pp, medium confidence |
| VITA-Bench | 25.6% | estimated ± 10.7 pp, low confidence |
| τ²-bench results | 91.2% | measured |
| AA Coding Index | 49.9% | estimated ± 5.3 pp, medium confidence |
| AA-MMMU-Pro | 69.9% | measured |
| APEX-Agents-AA | 25.5% | estimated ± 11.4 pp, low confidence |
| BioMysteryBench (human-difficult) | 18.0% | estimated ± 6.8 pp, low confidence |
| SWE-bench Verified | 74.8% | measured |
| BFCL v4 | 67.1% | estimated ± 8.5 pp, low confidence |
| JobBench | 3.2% | estimated ± 9.3 pp, low confidence |
| SWE-bench Pro | 52.7% | estimated ± 4.5 pp, high confidence |
| AA Agentic Index | 23.4% | estimated ± 12.7 pp, low confidence |
| MMLU-Pro | 83.3% | estimated ± 5.0 pp, medium confidence |
| AA-IFBench | 53.5% | measured |
| GPQA | 83.9% | estimated ± 6.1 pp, medium confidence |
| MMLU | 84.0% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 81.9% | estimated ± 3.2 pp, high confidence |
| Vals LiveCodeBench | 76.1% | estimated ± 10.0 pp, low confidence |
| Vals MMLU-Pro | 77.7% | estimated ± 2.9 pp, high confidence |
| MMMLU | 86.5% | estimated ± 0.7 pp, medium confidence |
| MMMU | 80.1% | estimated ± 2.7 pp, high confidence |
| AA MMLU-Pro | 84.0% | estimated ± 0.8 pp, medium confidence |
| ARC-AGI-1 | 75.6% | estimated ± 7.8 pp, low confidence |
| ARC-AGI-2 | 32.7% | estimated ± 14.4 pp, low confidence |
| FrontierCode 1.1 Main | 18.3% | estimated ± 4.2 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 6.8 pp, low confidence |
| OSWorld-Verified | 51.2% | estimated ± 3.8 pp, low confidence |
| ParseBench-1 | 53.7% | estimated ± 6.2 pp, medium confidence |
| Vals SWE-bench | 69.2% | estimated ± 6.6 pp, medium confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 53.1% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 58.6% | estimated ± 1.1 pp, low confidence |
| Chartography (tools) | 76.9% | estimated ± 4.1 pp, low confidence |
| DeepSWE | 38.1% | estimated ± 12.7 pp, low confidence |
| HLE w/o tools | 35.0% | estimated ± 4.9 pp, high confidence |
| ARC-AGI-3 | 1.3% | estimated ± 9.8 pp, medium confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| Vibe Code Bench | 2.1% | estimated ± 8.4 pp, medium confidence |
| ParseBench-2 | 57.8% | estimated ± 6.2 pp, medium confidence |
| CharXiv | 77.5% | estimated ± 6.3 pp, low confidence |
| CharXiv w/o tools | 76.8% | estimated ± 2.5 pp, medium confidence |
| AI2D_TEST | 88.1% | estimated ± 2.0 pp, medium confidence |
| C-Eval | 92.7% | estimated ± 1.0 pp, medium confidence |
| Claw-Eval | 45.2% | measured |
| CountBench | 91.4% | estimated ± 2.9 pp, low confidence |
| DynaMath | 69.4% | estimated ± 3.0 pp, low confidence |
| ERQA | 43.6% | estimated ± 3.1 pp, medium confidence |
| MathVision | 77.7% | estimated ± 3.1 pp, high confidence |
| MCP Atlas | 27.9% | estimated ± 13.5 pp, low confidence |
| MCP-Tasks | 48.7% | estimated ± 6.4 pp, low confidence |
| MMLU-Redux | 93.4% | estimated ± 0.8 pp, low confidence |
| MMMU-Pro | 71.3% | estimated ± 1.5 pp, high confidence |
| NL2Repo | 35.0% | estimated ± 6.2 pp, medium confidence |
| PostTrainBench v1 | 13.7% | estimated ± 5.5 pp, low confidence |
| RealWorldQA | 79.6% | estimated ± 2.9 pp, low confidence |
| ScreenSpot Pro | 71.2% | estimated ± 10.8 pp, low confidence |
| SuperGPQA | 64.7% | estimated ± 9.3 pp, low confidence |
| V* | 48.3% | estimated ± 7.5 pp, low confidence |
| Video-MME (w/o subtitle) | 79.7% | estimated ± 1.7 pp, medium confidence |
| Video-MME (with subtitle) | 81.7% | estimated ± 3.7 pp, low confidence |
| HealthBench Hard | 10.4% | estimated ± 8.6 pp, low confidence |
| MedXpertQA (MM) | 50.2% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 81.3% | estimated ± 4.0 pp, medium confidence |
| React Native Evals | 77.3% | estimated ± 2.7 pp, medium confidence |
| ResearchClawBench | 12.6% | estimated ± 1.3 pp, medium confidence |
| SWE-Rebench | 57.1% | estimated ± 3.6 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 30.2% | estimated ± 6.0 pp, low confidence |
| HealthBench (length-adjusted) | 46.8% | estimated ± 3.4 pp, low confidence |
| HealthBench Professional | 56.8% | estimated ± 4.2 pp, low confidence |
| HealthBench Professional (raw) | 42.0% | estimated ± 4.5 pp, medium confidence |
| STEMBench | 2.3% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 17.1% | estimated ± 4.3 pp, medium confidence |
| LiveCodeBench | 76.1% | estimated ± 14.6 pp, low confidence |
| BabyVision w/ Python | 84.2% | estimated ± 4.0 pp, low confidence |
| MRCRv2 | 84.2% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 61.2% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 33.9% | estimated ± 2.8 pp, low confidence |
| MMMU-Pro w/ Python | 73.6% | estimated ± 2.0 pp, high confidence |