MiMo-V2-Omni-0327: benchmark results
Provider: Xiaomi. Released 2026-03-27. Access: API.
Unified ELO 1625 ± 1, rank #337 of 1761 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CritPt | 90 | Accuracy (self-reported) | 97.7 |
| AA TAU-2 Bench | 88.01 | Accuracy (%) | 82.2 |
| AA Terminal-Bench Hard | 35.61 | Accuracy (%) | 82 |
| AA IFBench | 67.35 | Accuracy (%) | 80.6 |
| Artificial Analysis Intelligence Index | 29.44 | Intelligence Index | 80.3 |
| AA GPQA Diamond | 85.45 | Accuracy (%) | 78.8 |
| AA Humanity's Last Exam | 22.57 | Accuracy (%) | 75 |
| AA Long Context Reasoning | 73.33 | Accuracy (%) | 74.1 |
| AA Omniscience | -15.1 | Score | 68.2 |
| AA MMMU-Pro | 73.93 | Accuracy (%) | 64.7 |
| AA CritPt | 0.86 | Accuracy (%) | 62.5 |
| AA Omniscience - Science, Engineering & Mathematics | 29.53 | Accuracy (%) | 56.8 |
Interactive version: theaggregate.ai/model?slug=mimo-v2-omni-0327 · How It Works · Data refreshed daily, snapshot 2026-09-05.