Xiaomi
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
Xiaomi model releasesRank #75 across 566
Rank #57 across 222
Rank #49 across 371
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 37.2 | #75 |
| Artificial Analysis Coding Index | coding | 56.8 | #57 |
| GPQA | reasoning | 84.9% | #85 |
| Humanity's Last Exam | reasoning | 25.2% | #80 |
| SciCode |
| coding, reasoning |
| 43.1% |
| #93 |
| Output Speed | speed | 75.5 tok/s | #190 |
| Time to First Token | speed | 1.94s | #230 |
| Blended Price | cost | $0.175/M | #49 |
| Input Price | cost | $0.140/M | #60 |
| Output Price | cost | $0.280/M | #35 |
| Value Index | cost, overall | 212.6 | #6 |