Kimi
Kimi K2.5 (Reasoning)
Kimi K2.5 (Reasoning) is a Kimi language-model profile in the Easy Benchmarks snapshot. Use this page to compare its measured Artificial Analysis scores, output speed, time to first token, pricing, and relative ranking against other models in the local catalog.
Kimi model releasesOperational Metrics
Output Speed31.6 tok/s
First Token1.44s
Blended Price$1.20/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseJan 27, 2026
Context Windown/a
Modalitiesn/a
Strength: SciCode
Rank #24 across 472 models.
49.0%
Strength: HLE
Rank #25 across 474 models.
29.4%
Strength: GPQA
Rank #26 across 478 models.
87.9%
Watch Area: Speed
Rank #280 across 293 models.
31.6 tok/s
Watch Area: TTFT
Rank #203 across 293 models.
1.44s
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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 46.8 | #34 |
| Artificial Analysis Coding Index | coding | 39.5 | #47 |
| GPQA | reasoning | 87.9% | #26 |
| Humanity's Last Exam | reasoning | 29.4% | #25 |
| SciCode |