Back to models
Intelligence Index
Reasoning setting
37.9#27 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $0.14 in / $0.28 out / 1M tokXiaomi · direct API
- Context window
- 1M tok
Performance profile
CodingRank #30 of 94
51.3%
SciCodeCost efficiencyRank #5 of 67
607.4pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Reasoning mode
Integration
Reasoning trade-offs
Source (opens in a new tab)MiMo-V2.6-Flash
Cost per task (USD) · log scale
MiMo-V2.6-FlashThinking
- Intelligence Index
- 37.9
- Cost / task
- $0.0624
- Evaluation time
- 23.1m
Pricing & access
API route
XiaomiAPI
XiaomiAPITier & context
USD per 1M tokens
- Input
- $0.14
- Output
- $0.28
- Cached input
- $0.0028
Run locally
- Original download
- 172.9 GB
- App memory
- Unverified
- Documented software
- vLLMSetup guide (opens in a new tab)
Find GGUF downloadsBenchmarks
Full leaderboardSource (opens in a new tab)35.1%, rank 35 of 12651.3%, rank 30 of 9422.7%, rank 22 of 8774.3%, rank 54 of 1251,608 Elo, rank 17 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 32Agnes 2.5 Pro BetaReasoning37.5%
- 33Motif 3Reasoning37.0%
- 34Qwen3.7 PlusReasoning35.6%
- 35MiMo-V2.6-FlashReasoning35.1%
- 36Mistral Large 4Reasoning35.0%
- 36Kimi K2.7 CodeReasoning35.0%
- 38Beam 1.0Reasoning34.7%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherGPT-6 LunaMax
- Intelligence Index
- 38.1+0.2
- Cost / task
- $0.068+9%
- More from XiaomiMiMo-V2.6-ProReasoning
- Intelligence Index
- 46.3+8.4
- Cost / task
- $0.133+114%
- Similar scoreMistral Large 4Reasoning
- Intelligence Index
- 38.4+0.5
- Cost / task
- $1.13+1718%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.