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-V2.6-Pro
MiMo-V2.6-Pro is an open-weight model from Xiaomi, released Sep 21, 2026. It ranks #11 of 351 on the LMArena text leaderboard with a rating of 1491, and #14 of 27 on the Vals Index with 57.81%. It costs $0.43 per million input tokens and $0.87 per million output tokens, with a 1.1M-token context window.
- Developer
- Xiaomi
- Released
- Sep 21, 2026
- Context window
- 1.1M
- Price in / out, per 1M tokens
- $0.43 / $0.87
- Weights
- Open · MIT
- Inputs
- Text, Images, Video, Audio
- Reasoning
- Yes
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 59.3K
- Hugging Face likes
- 775
The rating LMArena published at each update since Sep 25, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| Vals IndexVals AI | 57.81% | 14 / 27 | $0.43 | |
| Terminal-Bench 4.0Coding | 31.31% | 21 / 55 | $0.50 | |
| Vibe Code BenchCoding | 85.22% | 15 / 115 | $1.04 | |
| Code MigrationCoding | 48.79% | 16 / 28 | $0.99 | |
| Finance AgentFinance | 64.26% | 10 / 31 | $0.18 | |
| Finance IndexFinance | 57.85% | 12 / 31 | $0.22 | |
| Tax Agent BenchFinance | 32.39% | 19 / 76 | $0.13 | |
| Legal IndexLaw | 72.14% | 8 / 28 | $0.18 | |
| Legal Research BenchLaw | 47.12% | 15 / 85 | $0.18 | |
| MedCodeMedicine | 44.97% | 39 / 107 | $0.435 / $0.87 | |
| Terminal-Bench ScienceReasoning | 2.86% | 33 / 42 | $0.62 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1491 | 11 / 351 | 4.1K |
| CodingLMArena | 1533 | 5 / 346 | 1.1K |
| MathLMArena | 1500 | 16 / 339 | 215 |
| Creative writingLMArena | 1466 | 20 / 349 | 792 |
| Instruction followingLMArena | 1491 | 12 / 351 | 1.4K |
| Hard promptsLMArena | 1511 | 8 / 351 | 2.6K |
| Multi-turnLMArena | 1465 | 42 / 349 | 582 |
| Long queriesLMArena | 1501 | 11 / 330 | 1.7K |
| ExpertLMArena | 1541 | 7 / 305 | 464 |
| Legal and governmentIndustries | 1485 | 26 / 325 | 347 |
| Medicine and healthcareIndustries | 1496 | 12 / 325 | 254 |
| Business and financeIndustries | 1469 | 23 / 344 | 715 |
| ChineseLanguages | 1531 | 21 / 328 | 299 |
| WebDevLMArena | 1625 | 23 / 124 | 5.7K |
| VisionLMArena | 1263 | 53 / 146 | 1.8K |
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-V2.6-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-V2.6-Pro?
MiMo-V2.6-Pro is made by Xiaomi, founded 2010 and based in Beijing.
How much does MiMo-V2.6-Pro cost?
$0.43 per million input tokens and $0.87 per million output tokens, at its provider’s list price.
What is MiMo-V2.6-Pro’s context window?
1.1M tokens (1,050,000).
How does MiMo-V2.6-Pro rank?
#11 of 351 on LMArena’s text leaderboard, rated 1491 (95% interval 1482–1500) from 4,067 votes, as of Oct 22, 2026.
Is MiMo-V2.6-Pro open source?
MiMo-V2.6-Pro has open weights under the MIT license, downloadable from Hugging Face (XiaomiMiMo/MiMo-V2.6-Pro-RL).