Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview
MiMo-V2.5-Pro
MiMo-V2.5-Pro is an open-weight model from Xiaomi, released Apr 22, 2026. It ranks #38 of 351 on the LMArena text leaderboard with a rating of 1464. It costs $0.30 per million input tokens and $0.61 per million output tokens, with a 1.1M-token context window.
- Developer
- Xiaomi
- Released
- Apr 22, 2026
- Context window
- 1.1M
- Price in / out, per 1M tokens
- $0.30 / $0.61
- Weights
- Open · MIT
- Inputs
- Text
- Reasoning
- Yes
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 12.9K
- Hugging Face likes
- 768
The rating LMArena published at each update since Apr 28, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| Terminal-Bench 4.0Coding | 0.51% | 53 / 55 | $0.23 | |
| SWE-benchCoding | 74.00% | 47 / 85 | $0.02 | |
| Vibe Code BenchCoding | 34.11% | 71 / 115 | $0.17 | |
| LiveCodeBenchCoding | 81.35% | 64 / 143 | $0.435 / $0.87 | |
| Tax Agent BenchFinance | 11.50% | 60 / 76 | $0.04 | |
| Legal Research BenchLaw | 15.87% | 65 / 85 | $0.08 | |
| MedCodeMedicine | 32.48% | 89 / 107 | $0.435 / $0.87 | |
| GPQA DiamondReasoning | 82.58% | 61 / 138 | $0.435 / $0.87 | |
| MMLU-ProReasoning | 84.59% | 62 / 138 | $0.435 / $0.87 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1464 | 38 / 351 | 77.9K |
| CodingLMArena | 1501 | 23 / 346 | 20.9K |
| MathLMArena | 1480 | 35 / 339 | 3.7K |
| Creative writingLMArena | 1438 | 50 / 349 | 14.6K |
| Instruction followingLMArena | 1475 | 26 / 351 | 26K |
| Hard promptsLMArena | 1486 | 26 / 351 | 50.7K |
| Multi-turnLMArena | 1475 | 30 / 349 | 13.1K |
| Long queriesLMArena | 1481 | 27 / 330 | 34.5K |
| ExpertLMArena | 1501 | 28 / 305 | 7.6K |
| Legal and governmentIndustries | 1474 | 38 / 325 | 6.3K |
| Medicine and healthcareIndustries | 1472 | 35 / 325 | 5.5K |
| Business and financeIndustries | 1466 | 26 / 344 | 14.9K |
| ChineseLanguages | 1506 | 47 / 328 | 5K |
| SpanishLanguages | 1468 | 34 / 249 | 2.4K |
| GermanLanguages | 1459 | 41 / 261 | 1.3K |
| FrenchLanguages | 1487 | 30 / 252 | 2.9K |
| JapaneseLanguages | 1410 | 67 / 236 | 1.1K |
| WebDevLMArena | 1481 | 69 / 124 | 22.8K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare MiMo-V2.5-Pro
Xiaomi
Xiaomi’s MiMo models are open reasoning models built for devices and cloud. Founded 2010, based in Beijing. xiaomimimo.github.io
Questions
Who makes MiMo-V2.5-Pro?
MiMo-V2.5-Pro is made by Xiaomi, founded 2010 and based in Beijing.
How much does MiMo-V2.5-Pro cost?
$0.30 per million input tokens and $0.61 per million output tokens, at its provider’s list price.
What is MiMo-V2.5-Pro’s context window?
1.1M tokens (1,050,000).
How does MiMo-V2.5-Pro rank?
#38 of 351 on LMArena’s text leaderboard, rated 1464 (95% interval 1461–1468) from 77,883 votes, as of Oct 22, 2026.
Is MiMo-V2.5-Pro open source?
MiMo-V2.5-Pro has open weights under the MIT license, downloadable from Hugging Face (XiaomiMiMo/MiMo-V2.5-Pro).