MiMo-V2.5-Pro

Xiaomi released 2026-04-22

$0.544 per million tokens, balanced

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

Intelligence42.9
Coding60.2
Agentic29.5
LMArena Elo1465default

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 window1.1M
Max output131K
Input modestext
Tool useyes
Reasoningoptional

Provenance

Price sourceopenrouter.ai
Fetched2026-08-24
Quality dataverified

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....

Markdown for LLMs