Inference
EN
Xiaomi

MiMo-V2-Pro

MiMo-V2-Pro is a reasoning model from Xiaomi. 10 benchmarks count toward its index, in 5 categories.

  • Closed weights
  • Reasoning
  • Input: text
  • Released 2026-03
RankedEnough results for an index.
IndexAll categories, out of 100.51.8±7.6Median 51.0
CoverageIndex weight that has results.75%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.1MMedian 262K
EloLMArena rating and rank.1437±5 #85Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.3 counted53.3110 / 218
CodingCode writing and repair.1 counted58.8—
ReasoningLogic problems and puzzles.2 counted45.8140 / 227
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.3 counted52.0120 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted53.3—
MathMath problems.None counted——

Results

10 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
τ²-Bench Tool-Agent-User EvaluationAgentic95.0%23 / 149
Software Engineering Benchmark VerifiedCoding78.0%29 / 114
Artificial Analysis GPQA DiamondKnowledge87.0%60 / 199
Artificial Analysis IFBenchInstruction68.8%49 / 146
Artificial Analysis Humanity's Last ExamKnowledge30.4%78 / 222
Artificial Analysis Long Context ReasoningReasoning68.3%122 / 217
Artificial Analysis Omniscience AccuracyKnowledge26.6%93 / 164
Critical Physics TasksReasoning0.3%137 / 214
Claw-EvalAgentic57.8%30 / 42
Gert Labs Composite Game BenchmarkAgentic36.7%44 / 52
ResearchClawBenchAgentic15.3%—

Sources

BenchLMCC BY-NC 4.0

History

5 releases
Index52.7 → 51.8
23 Oct 202612 Nov 2026

Questions

How good is MiMo-V2-Pro?
Its index is 51.8 out of 100. That is place 137 of 283 ranked models.
What is MiMo-V2-Pro best at?
Knowledge: 52.0 out of 100, place 120 of 268.
What is the context window of MiMo-V2-Pro?
1M tokens.
Is MiMo-V2-Pro open source?
No. Its weights are not published.
When was MiMo-V2-Pro released?
March 2026.

Badge

MiMo-V2-Pro on Inference360: place 137 of 283, index 51.8
HTML
<a href="https://inference360.ai/models/mimo-v2-pro"><img src="https://inference360.ai/badges/mimo-v2-pro.svg" alt="MiMo-V2-Pro on Inference360: place 137 of 283, index 51.8" height="20"></a>
Markdown
[![MiMo-V2-Pro on Inference360: place 137 of 283, index 51.8](https://inference360.ai/badges/mimo-v2-pro.svg)](https://inference360.ai/models/mimo-v2-pro)

Compare with

o351.8Qwen3.5-122B-A10B51.9GLM-551.6MiMo-V2-Omni47.2MiMo-V2-Flash43.4

More from Xiaomi

All models
MiMo-V2-Omni47.2MiMo-V2-Flash43.4MiMo-V2.5-Pro56.3MiMo-V2.554.8MiMo V2.6 Pro UltraSpeedUnranked