Inference
EN
Xiaomi

MiMo-V2-Omni

MiMo-V2-Omni is a reasoning model from Xiaomi. 10 benchmarks count toward its index, in 6 categories.

  • Closed weights
  • Reasoning
  • Input: text
  • Released 2026-03
RankedEnough results for an index.
IndexAll categories, out of 100.47.2±6.6Median 51.0
CoverageIndex weight that has results.85%
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.262KMedian 262K
EloLMArena rating and rank.1423±6 #110Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.2 counted46.9156 / 218
CodingCode writing and repair.1 counted56.4—
ReasoningLogic problems and puzzles.2 counted48.9123 / 227
MultimodalTasks with images and text.1 counted46.1—
KnowledgeFacts and expert knowledge.3 counted44.9168 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted39.0—
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 EvaluationAgentic91.2%39 / 149
Software Engineering Benchmark VerifiedCoding74.8%45 / 114
Artificial Analysis Long Context ReasoningReasoning75.0%95 / 217
Artificial Analysis GPQA DiamondKnowledge82.8%90 / 199
Artificial Analysis Humanity's Last ExamKnowledge22.1%107 / 222
Artificial Analysis IFBenchInstruction53.5%75 / 146
Critical Physics TasksReasoning1.1%118 / 214
Artificial Analysis MMMU-ProMultimodal69.9%75 / 113
Artificial Analysis Omniscience AccuracyKnowledge19.3%135 / 164
Claw-EvalAgentic45.2%40 / 42

Sources

BenchLMCC BY-NC 4.0

History

5 releases
Index48.1 → 47.2
23 Oct 202612 Nov 2026

Questions

How good is MiMo-V2-Omni?
Its index is 47.2 out of 100. That is place 167 of 283 ranked models.
What is MiMo-V2-Omni best at?
Reasoning: 48.9 out of 100, place 123 of 227.
What is the context window of MiMo-V2-Omni?
262K tokens.
Is MiMo-V2-Omni open source?
No. Its weights are not published.
When was MiMo-V2-Omni released?
March 2026.

Badge

MiMo-V2-Omni on Inference360: place 167 of 283, index 47.2
HTML
<a href="https://inference360.ai/models/mimo-v2-omni"><img src="https://inference360.ai/badges/mimo-v2-omni.svg" alt="MiMo-V2-Omni on Inference360: place 167 of 283, index 47.2" height="20"></a>
Markdown
[![MiMo-V2-Omni on Inference360: place 167 of 283, index 47.2](https://inference360.ai/badges/mimo-v2-omni.svg)](https://inference360.ai/models/mimo-v2-omni)

Compare with

Grok 4.1 Fast (Reasoning)47.3Claude 4 Opus Thinking47.0Claude 4.1 Opus Thinking47.0MiMo-V2-Pro51.8MiMo-V2.5-Pro56.3

More from Xiaomi

All models
MiMo-V2-Pro51.8MiMo-V2-Flash43.4MiMo-V2.5-Pro56.3MiMo-V2.554.8MiMo V2.6 Pro UltraSpeedUnranked