MiMo-V2.5-Pro
XiaomiProprietaryReasoningVerifiedReleased Apr 22, 2026Input: text
Overall score
53.0
Rank 87 of 222 · 36.0–70.0
Context window
1M
1,000,000 tokens
Price per 1M tokens
$0.43 in · $0.87 out
Source: OpenRouter
Blended price
$0.54
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#793.8
- 2Reasoning79.8
- 3Agentic & tool use70.7
- 4Knowledge#7365.0
- 5Coding49.1
Benchmark results (9)
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 | 62.70 | #9 of 52 |
| MazeBench | 0 | #20 of 42 |
| Terminal-Bench 2.0 | 68.4 | #8 of 39 |
| Claw-Eval | 63.8 | #15 of 36 |
| τ³-bench results | 72.9 | #3 of 23 |
Knowledge
| HLE | 48.0 | #19 of 69 |
| HLE w/o tools | 34.0 | #27 of 43 |
Coding
| SWE-bench Pro | 57.2 | #37 of 69 |
Multimodal
| Design Arena Website | 1267 | #31 of 91 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price (OpenRouter) | $0.43 | $0.87 | — |
| OpenRouter xiaomi/mimo-v2.5-pro | $0.43 | $0.87 | $0.004 |
We did not find a current first-party public API pricing page for Xiaomi MiMo-V2.5-Pro. BenchLM treats pricing as unavailable until Xiaomi publishes one.
Arena ratings
Human-preference ratings from LMArena. Best-rated variant shown.
| Text | 1465 | #37 · 75.7K votes |
| WebDev (coding) | 1480 | #68 · 22.5K votes |
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.
Related models
Same family
- MiMo-V2.5—
- MiMo-V2-Pro52.9
Similar score
- Kimi K2.553.0 · $1.20
- Grok 4.353.1 · $1.56
- MiMo-V2-Pro52.9 · —
- GLM-5-Turbo53.2 · $1.90
- MAI-Thinking-153.3 · —