Kimi K2.5 (Non-reasoning): benchmark results
Kimi K2.5 evaluated with reasoning disabled. Provider: Moonshot. Released 2026-01-27. Access: Open.
Aggregate Rating 1648 ± 8, rank #526 of 2168 rated models, from 243 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Chronicles-OCR - Archaic Character Recognition | 27.1 | Exact-match accuracy (%) of the modern character given for a | 100 |
| Chronicles-OCR - Mature Script Classification | 77 | Accuracy (%) of classifying the image into one of the Seven | 100 |
| DiffCap-Bench - Background | 90 | Macro-averaged F1* (%) on background changes: harmonic mean | 100 |
| ChartArena - Combination Chart (English) | 33.6 | mAP-high (%) on English combination charts, each model parse | 97.7 |
| ChartArena - Line Chart (English) | 60.9 | mAP-high (%) on English line charts, each model parses the c | 97.7 |
| ChartArena - Combination Chart (Chinese) | 63.6 | mAP-high (%) on Chinese combination charts, each model parse | 97.6 |
| ChartArena - English | 54.8 | mAP-high (%) averaged over the eight chart types (bar, line, | 97.6 |
| ChartArena - Radar Chart (Chinese) | 59.7 | mAP-high (%) on Chinese radar charts, each model parses the | 97.6 |
| Chronicles-OCR - Archaic Text Parsing | 0.22 | Paragraph-level normalized edit similarity (0-1: one minus t | 96.4 |
| ChartArena - Radar Chart (English) | 30.2 | mAP-high (%) on English radar charts, each model parses the | 95.3 |
| ChartArena - Box Plot (Chinese) | 47.6 | mAP-high (%) on Chinese box plots, each model parses the cha | 95.2 |
| ChartArena - Line Chart (Chinese) | 79.8 | mAP-high (%) on Chinese line charts, each model parses the c | 95.2 |
Interactive version: theaggregate.ai/model?slug=kimi-k2-5-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.