KAT-Coder-Pro V2.5: benchmark results
Provider: Kuaishou. Released 2026-07-10. Access: API.
Unified ELO 1840 ± 23, rank #100 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenchmarkList ECI | 134.57 | Capability Index (ECI) | 84.2 |
| AI Chess Leaderboard (Reasoning) | 718 | Elo | 55.1 |
| ObviousBench | 90.97 | Answer pass³ (%) | 50.4 |
| Gert Labs Rankings | 37.67 | GScore (%) | 44.4 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 92 | Questions answered with a valid query on the first attempt ( | 40.5 |
| Tinybird AI SQL Benchmark - Success Rate | 98 | Questions answered with a valid query within 3 retries (%) | 35.5 |
| KiloBench - Terminal Bench 2.0 | 50.34 | Task completion in Kilo's agent harness, mean of 5 attempts | 33.3 |
| Tinybird AI SQL Benchmark - Exactness | 43.99 | Result exactness vs human reference queries (0-100) | 30.7 |
| SvelteBench | 82.2 | Average pass@1 (%) | 30.6 |
| LM Market Cap LMC Score | 40 | LMC Score (0-100) | 28 |
| AI Chess Leaderboard (Continuation) | 466 | Elo | 26.3 |
Interactive version: theaggregate.ai/model?slug=kat-coder-pro-v2-5 · How It Works · Data refreshed daily, snapshot 2026-09-19.