KAT-Coder-Pro V1
KAT-Coder-Pro V1 is KwaiKAT's most advanced agentic coding model in the KAT-Coder series. Designed specifically for agentic coding tasks, it excels in real-world software engineering scenarios, achieving 73.4% solve rate on the SWE-Bench Verified benchmark. 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.
Specifications
Modalities
Supported Parameters
Max Output Tokens
128,000Data policy
- Prompt retention
- Unknown — we could not confirm
- Training
- Unknown — not declared
"Unknown" does not mean "safe". It means we could not confirm it.
Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.
Frequently asked questions
- Is KAT-Coder-Pro V1 available on FastMetal?
- Not at the moment. GLM 5.3 Flash, from the same lab, is available on the FastMetal API today.
- What is the context window of KAT-Coder-Pro V1?
- 256,000 tokens, shared between the prompt and the response.
- How does KAT-Coder-Pro V1 rank?
- #136 on the public arena's Overall board (ELO 1,256). Ranks move as the leaderboard is updated.
Leaderboard
Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-23; category names mapped and ratings rounded by FastMetal.