Kimi K2.5open
Moonshot AI
64.7#64 of 427 overall
- Input / output
- US$ 0,50 / US$ 2,50 US$ per 1M tokens
- Context
- 262K tokens
- Release
- 01/27/2026 release date
- Speed
- 0 tok/s first token in 0.00 s
Family history
The 4 versions of this family, from first to newest, by release date. Click a point to open that version.
See the data as a table
| Model | Released | Score | Rank | AA Intel. | Elo Arena |
|---|---|---|---|---|---|
| Kimi K2 Thinking | 11/06/2025 | 50.2 | #148 | — | 1380 |
| Kimi K2.5 | 01/27/2026 | 64.7 | #64 | — | 1445 |
| Kimi K2.6 | 04/20/2026 | 67.7 | #51 | — | 1456 |
| Kimi K3 | 07/16/2026 | 56.4 | #98 | 17.4 | 1476 |
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| Arena text (Elo) weight 2 | 1445 | 75% | LMArena |
| Arena WebDev (Elo) weight 1 | 1436 | 43% | LMArena |
| Arena vision (Elo) weight 0.5 | 1269 | 66% | LMArena |
| Humanity's Last Exam weight 1 | 30.7 | 80% | Artificial Analysis |
| GPQA Diamond | 87.9 | 86% | Artificial Analysis |
| Long-context reasoning | 78.0 | 79% | Artificial Analysis |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Coding | 46.4 | #67 | Arena WebDev (Elo) |
| Reasoning | 72.0 | #64 | Humanity's Last Exam, GPQA Diamond |
| Research | 64.5 | #67 | Long-context reasoning |
| Design | 46.4 | #67 | Arena WebDev (Elo) |
| Chat | 62.5 | #49 | Arena text (Elo) |
| Vision | 57.9 | #36 | Arena vision (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.