Kimi
Kimi K2 Thinking
Kimi K2 Thinking is an advanced open-source thinking model by Moonshot AI. It can execute up to 200 – 300 sequential tool calls without human interference, reasoning coherently across hundreds of steps to solve complex problems. Built as a thinking agent, it reasons step by step while using tools, achieving state-of-the-art performance on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks, with major gains in reasoning, agentic search, coding, writing, and general capabilities.
Kimi model releasesModel Snapshot
TypeLanguage
ReleaseNov 6, 2025
Context262,114
Tagsreasoning, tool-use, implicit-caching
Overall
Rank #70 across 526
40.9
Coding
Rank #95 across 436
34.8
Blended Price
Rank #209 across 357
$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 Speed131.1 tok/s
First Token0.86s
Max Output262,114
Pricing
Blended$1.08/M
Input$0.600/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 40.9 | #70 |
| Artificial Analysis Coding Index | coding | 34.8 | #95 |
| Artificial Analysis Math Index | math | 94.7 | #11 |
| MMLU-Pro | reasoning | 84.8% | #36 |