MiMo-V2.5
XiaomiProprietaryReasoningReleased Apr 22, 2026Input: text, audio, image, video
Overall score
—
Not enough evidence to rank yet
Context window
1M
1,000,000 tokens
Price per 1M tokens
$0.14 in · $0.28 out
Source: OpenRouter
Blended price
$0.17
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.
- 1Multimodal#3272.2
- 2Agentic & tool use66.0
- 3Knowledge53.9
- 4Coding47.8
Benchmark results (10)
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 | 46.89 | #26 of 52 |
| Terminal-Bench 2.0 | 65.8 | #11 of 39 |
| Claw-Eval | 62.3 | #19 of 36 |
| ResearchClawBench | 16.9 | #12 of 19 |
| MM-ClawBench | 23.8 | #2 of 2 |
Multimodal
| Design Arena Website | 1266 | #32 of 91 |
| MMMU-Pro | 77.9 | #24 of 48 |
| CharXiv | 81.0 | #24 of 42 |
| Video-MME (with subtitle) | 87.7 | #4 of 11 |
Coding
| SWE-bench Pro | 56.1 | #44 of 69 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price (OpenRouter) | $0.14 | $0.28 | — |
| OpenRouter xiaomi/mimo-v2.5 | $0.14 | $0.28 | $0.003 |
We did not find a current first-party public API pricing page for Xiaomi MiMo-V2.5. BenchLM treats pricing as unavailable until Xiaomi publishes one.
Arena ratings
Human-preference ratings from LMArena. Best-rated variant shown.
| Text | 1428 | #100 · 47.4K votes |
| WebDev (coding) | 1438 | #80 · 14.9K votes |
| Vision | 1247 | #66 · 29.4K votes |
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.
Related models
Same family
- MiMo-V2.5-Pro53.0
- MiMo-V2-Omni50.0