Back to models
Intelligence Index
Reasoning setting
25.8#40 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- ≈ $0.67 in / $3.35 out / 1M tokOpenRouter · Inceptron · INT4
- Context window
- 256K tok
Performance profile
ReasoningRank #22 of 107
89.6%
GPQA DiamondCodingRank #40 of 94
47.8%
SciCodeCost efficiencyRank #39 of 67
47.7pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Measured setting
Integration
Reasoning trade-offs
Source (opens in a new tab)Kimi K2.7 Code
Cost per task (USD) · log scale
Kimi K2.7 CodeReasoning
- Intelligence Index
- 25.8
- Cost / task
- $0.5412
- Evaluation time
- 9.5m
Pricing & access
USD per 1M tokens
- Input
- $0.6712
- Output
- $3.35
- Cached input
- $0.18
Run locally
- Original download
- 595.2 GB
- App memory
- Unverified
- Documented software
- vLLMSetup guide (opens in a new tab)
Find GGUF downloadsBenchmarks
Full leaderboardSource (opens in a new tab)35.0%, rank 36 of 12647.8%, rank 40 of 941.0%, rank 39 of 8779.3%, rank 37 of 1251,038 Elo, rank 49 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 34Qwen3.7 PlusReasoning35.6%
- 35MiMo-V2.6-FlashReasoning35.1%
- 36Mistral Large 4Reasoning35.0%
- 36Kimi K2.7 CodeReasoning35.0%
- 38Beam 1.0Reasoning34.7%
- 39DeepSeek V4 Flash VisionMax34.5%
- 40Apodex 1.1Reasoning34.1%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherGPT-5.5 Instant (June 2026)Reasoning
- Intelligence Index
- 26.0+0.2
- Cost / task
- $0.691+28%
- Higher score, lower costMiMo-V2.6-ProReasoning
- Intelligence Index
- 46.3+20.5
- Cost / task
- $0.133−75%
- More from Moonshot AIKimi-K3Max
- Intelligence Index
- 43.6+17.8
- Cost / task
- $2.00+270%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.