Kimi K2.5 (Non-reasoning) — benchmark results
Kimi K2.5 evaluated with reasoning disabled. Provider: Moonshot. Released 2026-01-27. Access: Open.
Unified ELO 1652 ± 30, rank #363 of 1776 rated models, from 79 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Natural Intelligence | 60.32 | NatInt Score | 94.7 |
| UGI - Writing | 61.51 | Writing Score | 94.4 |
| AA Omniscience - Software Engineering (SWE) - PHP | 46 | Accuracy (%) | 80.8 |
| AA Omniscience - Software Engineering (SWE) - Rust | 66 | Accuracy (%) | 80.6 |
| CLEM PrivateShared | 92.69 | Game Clemscore (%) | 79.3 |
| AA Omniscience - Software Engineering (SWE) - Python | 37.5 | Accuracy (%) | 78.6 |
| AA Omniscience - Software Engineering (SWE) - HTML | 48 | Accuracy (%) | 77.7 |
| AA Omniscience - Software Engineering (SWE) - R | 30 | Accuracy (%) | 77.7 |
| UGI Leaderboard | 44 | UGI Score | 77.5 |
| CLEM TextMapWorld GraphReasoning | 73.16 | Game Clemscore (%) | 76.9 |
| AA Omniscience - Software Engineering (SWE) - Go | 32 | Accuracy (%) | 76.8 |
| CLEM Deal or No Deal | 78.59 | Game Clemscore (%) | 76.7 |
Interactive version: theaggregate.ai/model?slug=kimi-k2-5-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.