Kimi
Kimi K2.5 (Non-reasoning)
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...
Kimi model releasesModel Snapshot
ReleaseJan 27, 2026
Context262,144
Overall
Rank #140 across 566
29.4
Coding
Rank #87 across 222
46.8
Blended Price
Rank #196 across 371
$1.20/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 Speed46 tok/s
First Token1.13s
Max Output262,144
Pricing
Blended$1.20/M
Input$0.600/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 29.4 | #140 |
| Artificial Analysis Coding Index | coding | 46.8 | #87 |
| GPQA | reasoning | 78.9% | #156 |
| Humanity's Last Exam | reasoning | 12.3% | #167 |
| SciCode |