- MMAU-Pro 69.4
- BigBench Audio 94
- MMMU-Pro 76.8
- CharXiv RQ 80.1
- Video-MME 85.3
- FutureOmni 66.7
- MM-BrowserComp 52
- OmniGAIA 49.8
- Claw Eval 54.8
- SWE-Bench Verified 74.8
- GDPVal (Elo) 1410
- PinchBench (avg.) 81.2
MiMo-V2-Omni
MiMo-V2-Omni ranks first on MM-BrowseComp.
18
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
Xiaomi Corp Mar 2026
MiMo-V2-Omni
Closed weights Mid-size
No Epoch Capabilities Index score yet
- MMMU-Pro 76.8% #28 /72
- Claw-Eval 72.4% #20 /23
- Claw-Eval Pass^3 45.2% #21 /23
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMArena (Elo) | 1,431 | #91 of 333 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-bench Verified | 74.8% | #44 of 150 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MM-BrowseComp | 52% | #1 of 5 | Model card | |
| SnakeBench | 20 | #126 of 183 | Official leaderboard | |
| PinchBench | 81.2% | #11 of 13 | Model card | |
| Claw-Eval | 72.4% | #20 of 23 | Official leaderboard | |
| Claw-Eval Pass^3 | 45.2% | #21 of 23 | Official leaderboard | |
| OmniGAIA | 49.8% | #3 of 3 | Model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GDPval-AA | 1,410 | #13 of 16 | Model card |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| VideoMME v2 (with subtitles) | 38.6% | #6 of 31 | Official leaderboard | |
| MMMU-Pro | 76.8% | #28 of 72 | Model card | |
| Video-MME | 85.3% | #17 of 42 | Model card | |
| Vision Arena | 1,216 | #67 of 136 | Official leaderboard | |
| MMAU-Pro | 69.4% | #1 of 2 | Model card | |
| CharXiv | 80.1% | #35 of 67 | Model card | |
| Big Bench Audio | 94% | #4 of 6 | Model card | |
| Claw-Eval-MM | 44.4% | #11 of 11 | Official leaderboard | |
| FutureOmni | 66.7% | #1 of 1 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.