MiMo-V2.5
Xiaomi released 2026-04-22
DeepSeek V4 Flash 0731 scores higher and costs less — but you would give something up.
+13.8 on the capability index and 40% cheaper ($0.105/M against $0.175/M). What you lose:
- no audio, image, video input
Capability scores do not measure context length, output ceiling or which inputs a model accepts, so a higher score does not mean a drop-in replacement.
Every price dimension
| Input | $0.140/M |
|---|---|
| Output | $0.280/M |
| Cached input | $0.0028/M |
Independent scores
| Intelligence | 38 |
|---|---|
| Coding | 56.8 |
| Agentic | 24.4 |
| LMArena Elo | 1427.3default |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Best rankings by task
- dataviz #21of 142 1273
- website #23of 151 1289
- codecategories #23of 145 1285
- uicomponent #24of 140 1285
- gamedev #25of 144 1278
- svg #27of 98 1213
- 3d #30of 136 1259
Capability
| Context window | 1.1M |
|---|---|
| Max output | 131K |
| Input modes | text, audio, image, video |
| Tool use | yes |
| Reasoning | optional |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
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...