MiMo-V2-Omni: benchmark results
Xiaomi's omni-modal MiMo-V2 model unifying text, vision, and speech in one backbone. Provider: Xiaomi. Released 2026-03-11. Access: API.
Aggregate Rating 1678 ± 9, rank #253 of 1656 rated models, from 229 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (PinchBench - Xiaomi MiMo V2 Launch Average) | 81.2 | Average Score (%) | 100 |
| Video-MME-v2 - Level 1 Retrieval & Aggregation (w/o subs) | 38.67 | Level 1 Score w/o sub (%) | 91.7 |
| ChartArena - Mind Map (English) | 76.6 | mAP-high (%) on English mind maps, each model parses the cha | 91 |
| Video-MME-v2 | 47.1 | Avg Accuracy w/o sub (%) | 89.6 |
| Video-MME-v2 - Level 2 Temporal Understanding (w/o subs) | 35.98 | Level 2 Score w/o sub (%) | 89.6 |
| Video-MME-v2 - Non-Lin Score (w/o subs) | 29.93 | Non-Lin Score w/o sub (%) | 89.6 |
| UAV-DualCog - Landmark Visibility Counting | 55.8 | Visibility-count accuracy (%; 1,024 flight videos in which t | 89.3 |
| Video-MME-v2 - Level 3 Complex Reasoning (w/o subs) | 20.37 | Level 3 Score w/o sub (%) | 87.5 |
| ChartArena - Flowchart (Chinese) | 51 | mAP-high (%) on Chinese flowcharts, each model parses the ch | 86.5 |
| AA TAU-2 Bench | 91.23 | Accuracy (%) | 86.1 |
| ChartArena - Pie Chart (English) | 87 | mAP-high (%) on English pie charts, each model parses the ch | 86 |
| Tau2-Bench Telecom | 91.23 | Success Rate (%) | 85.8 |
Interactive version: theaggregate.ai/model?slug=mimo-v2-omni · How It Works · Data refreshed daily, snapshot 2026-10-20.