KAT Coder Pro V2 — benchmark results
Kwaipilot's flagship agentic-coding KAT-Coder successor (MoE, 72B active). Provider: Kuaishou. Released 2026-03-27. Access: API.
Unified ELO 1689 ± 28, rank #295 of 1776 rated models, from 41 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Terminal-Bench Hard | 49.24 | Accuracy (%) | 94.5 |
| AA-LCR | 66 | Score (self-reported) | 87 |
| AA GPQA Diamond | 85.45 | Accuracy (%) | 84.7 |
| AA Long Context Reasoning | 66 | Accuracy (%) | 84.1 |
| AA TAU-2 Bench | 89.47 | Accuracy (%) | 83.9 |
| Artificial Analysis Intelligence Index | 33.69 | Intelligence Index | 81.2 |
| AA IFBench | 66.67 | Accuracy (%) | 79.5 |
| Wolfram LLM Benchmarking Project | 53.8 | Correct Functionality (%) | 79.5 |
| SnakeBench | 27 | TrueSkill Rating | 77 |
| AA Humanity's Last Exam | 15.99 | Accuracy (%) | 75 |
| AA Omniscience | -21.6 | Score | 70.1 |
| AA Omniscience - Software Engineering (SWE) - C | 49 | Accuracy (%) | 68.8 |
Interactive version: theaggregate.ai/model?slug=kat-coder-pro-v2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.