Kimi
Kimi K2 Thinking
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
Kimi model releasesModel Snapshot
ReleaseNov 6, 2025
Context262,144
Overall
Rank #113 across 566
32.7
Coding
Rank #164 across 222
21.0
Blended Price
Rank #185 across 371
$1.08/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed131 tok/s
First Token0.80s
Max Output262,144
Pricing
Blended$1.08/M
Input$0.600/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 32.7 | #113 |
| Artificial Analysis Coding Index | coding | 21.0 | #164 |
| Artificial Analysis Math Index | math | 94.7 | #11 |
| MMLU-Pro | reasoning | 84.8% | #40 |