MiMo-V2-Omni — benchmark results
Xiaomi's omni-modal MiMo-V2 model unifying text, vision, and speech in one backbone. Provider: Xiaomi. Released 2026-03-18. Access: Open.
Unified ELO 1673 ± 23, rank #316 of 1776 rated models, from 54 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA-LCR | 66.7 | Score (self-reported) | 89.2 |
| Video-MME-v2 | 47.1 | Avg Accuracy w/o sub (%) | 87.8 |
| AA Long Context Reasoning | 66.67 | Accuracy (%) | 86.2 |
| AA TAU-2 Bench | 91.23 | Accuracy (%) | 86.1 |
| Artificial Analysis Intelligence Index | 34.99 | Intelligence Index | 83.8 |
| BenchLM | 63.1 | Overall Score | 81.2 |
| AA Terminal-Bench Hard | 34.85 | Accuracy (%) | 80.3 |
| AA Humanity's Last Exam | 19.93 | Accuracy (%) | 80.1 |
| AA GPQA Diamond | 82.83 | Accuracy (%) | 78.2 |
| Chatbot Arena (Text) | 1430 | Elo | 77.8 |
| CritPt | 1.1 | Accuracy (self-reported) | 77.4 |
| AI Chess Leaderboard (Reasoning) | 876 | Elo | 76.9 |
Interactive version: theaggregate.ai/model?slug=mimo-v2-omni · How the rankings work · Data refreshed daily, snapshot 2026-07-22.