MiMo-V2.5-Pro
Xiaomi released 2026-04-22
DeepSeek V4 Flash 0731 is both better and cheaper.
It scores +8.9 higher and costs 81% less ($0.105/M against $0.544/M) on this workload — and it does everything this model does.
GPT-5.6 Luna is cheaper still (17% less) but drops 131K → 128K max output.
Every price dimension
| Input | $0.435/M |
|---|---|
| Output | $0.870/M |
| Cached input | $0.0036/M |
Independent scores
| Intelligence | 42.9 |
|---|---|
| Coding | 60.2 |
| Agentic | 29.5 |
| LMArena Elo | 1465default |
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
- website #15of 151 1295
- gamedev #17of 144 1301
- dataviz #17of 142 1286
- codecategories #18of 145 1298
- 3d #21of 136 1294
- svg #22of 98 1223
- uicomponent #23of 140 1288
Capability
| Context window | 1.1M |
|---|---|
| Max output | 131K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....