Kimi
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
Kimi model releasesRank #36 across 566
Rank #42 across 222
Rank #228 across 371
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Higher bars mean stronger relative placement.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 44.2 | #36 |
| Artificial Analysis Coding Index | coding | 61.8 | #42 |
| LiveBench Mathematics | math | 84.3% | #22 |
| GPQA | reasoning | 91.1% | #22 |
| Humanity's Last Exam |
| reasoning |
| 35.9% |
| #32 |
| SciCode | coding, reasoning | 53.5% | #20 |
| Output Speed | speed | 39.2 tok/s | #292 |
| Time to First Token | speed | 1.13s | #164 |
| Blended Price | cost | $1.71/M | #228 |
| Input Price | cost | $0.950/M | #220 |
| Output Price | cost | $4.00/M | #223 |
| Value Index | cost, overall | 25.8 | #130 |