MiMo-V2-Pro
XiaomiProprietaryReasoningProvisionalReleased Mar 18, 2026
Overall score
52.9
Rank 88 of 222 · 43.2–62.7
Context window
1M
1,000,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Instruction following#5184.0
- 2Reasoning71.9
- 3Knowledge49.5
Benchmark results (4)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Agentic & tool use
| Gert Labs | 36.68 | #44 of 52 |
| Claw-Eval | 57.8 | #25 of 36 |
| ResearchClawBench | 15.3 | #13 of 19 |
Coding
| SWE-bench Verified | 78.0 | #26 of 98 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price | — | — | — |
Arena ratings
Human-preference ratings from LMArena. Best-rated variant shown.
| Text | 1436 | #85 · 25.4K votes |
| WebDev (coding) | 1434 | #86 · 7.2K votes |
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.
Related models
Same family
- MiMo-V2-Flash41.0
- MiMo-V2-Omni50.0
Similar score
- MiMo-V2.5-Pro53.0 · $0.54
- Kimi K2.553.0 · $1.20
- Grok 4.353.1 · $1.56
- Inkling-Small52.7 · $0.80
- GLM-5-Turbo53.2 · $1.90