KwaiKAT
KAT-Coder-Pro V1 is KwaiKAT's most advanced agentic coding model in the KwaiKAT series. Designed specifically for agentic coding tasks, it excels in real-world software engineering scenarios, achieving a remarkable 73.4% solve rate on the SWE-Bench Verified benchmark. KAT-Coder-Pro V1 delivers top-tier coding performance and has been rigorously tested by thousands of in-house engineers. The model has been optimized for tool-use capability, multi-turn interaction, instruction following, generalization and comprehensive capabilities through a multi-stage training process, including mid-training, supervised fine-tuning (SFT), reinforcement fine-tuning (RFT), and scalable agentic RL.
KwaiKAT model releasesRank #175 across 600
No rank
No rank
Percentile score by analysis domain.
Higher bars mean stronger relative placement.
Streaming speed is not measured for this model yet.
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 28.3 | #175 |
| Artificial Analysis Math Index | math | 94.7 | #10 |
| MMLU-Pro | reasoning | 81.3% | #79 |
| GPQA | reasoning | 76.4% | #200 |
| Humanity's Last Exam |
| reasoning |
| 33.4% |
| #49 |
| LiveCodeBench | coding | 74.7% | #49 |
| SciCode | coding, reasoning | 36.6% | #226 |