Kimi
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
Kimi model releasesRank #230 across 566
No rank
Rank #184 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 | 19.4 | #230 |
| Artificial Analysis Math Index | math | 57.0 | #124 |
| MMLU-Pro | reasoning | 82.4% | #73 |
| GPQA | reasoning | 76.6% | #185 |
| Humanity's Last Exam |
| reasoning |
| 7.0% |
| #265 |
| LiveCodeBench | coding | 55.6% | #130 |
| SciCode | coding, reasoning | 34.5% | #249 |
| MATH-500 | math | 97.1% | #26 |
| AIME | math | 69.3% | #41 |
| Output Speed | speed | 36.7 tok/s | #298 |
| Time to First Token | speed | 0.99s | #133 |
| Blended Price | cost | $1.04/M | #184 |
| Input Price | cost | $0.585/M | #182 |
| Output Price | cost | $2.40/M | #172 |
| Value Index | cost, overall | 18.7 | #174 |