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.
No benchmark data available yet.
- Typetext
- Context256K tokens (~128 books)
- ReleasedNov 2025
- LicenseProprietary
- StatusActive
- Cost / Message~$0.001
Frequently Asked Questions
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenBenchmarks
Key facts · as of 2026-03-27
- KAT-Coder-Pro V1 by kwaipilot. Not enough public benchmark scores to rank yet.
- List price $0.21 input · $0.83 output per 1M tokens (as of 2026-03-27).
How to cite · data as of 2026-03-27
KAT-Coder-Pro V1 · benchmarks, pricing and providers. BenchGecko, data as of 2026-03-27. https://benchgecko.ai/model/kat-coder-pro
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP