Kimi
Kimi K2.6 (Non-reasoning)
Kimi K2.6 demonstrates particularly strong performance in long-horizon coding tasks and produces professional-grade design with code and vision.
Kimi model releasesModel Snapshot
TypeLanguage
ReleaseApr 20, 2026
Context262,000
Tagsreasoning, tool-use, vision, file-input
Overall
Rank #54 across 526
42.9
Coding
Rank #66 across 436
38.4
Blended Price
Rank #245 across 357
$1.71/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 Speed39 tok/s
First Token1.32s
Max Output262,000
Pricing
Blended$1.71/M
Input$0.950/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 42.9 | #54 |
| Artificial Analysis Coding Index | coding | 38.4 | #66 |
| GPQA | reasoning | 78.8% | #128 |
| Humanity's Last Exam | reasoning | 18.2% | #93 |
| SciCode |