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.

Share

Model details

Context window256,000 tokens
Max completion size73 tokens
Prompt cost / 1K tokens$0.000000207
Completion cost / 1K tokens$0.000000828
Accepts
Produces

Benchmark performance

Overall

68
score
17th
placement

Cost

97
score
4th
placement

Logic

80
score
7th
placement

Speed

81
score
19th
placement

Scoring

8
score
25th
placement

Tool Use

45
score
5th
placement

Hallucination

89
score
5th
placement

Classification

19
score
4th
placement

Structured Output

83
score
3rd
placement

Pricing

Usage pricing
Prompt
$0.000000207
Completion
$0.000000828
Request
FREE
Image
FREE
Web Search
FREE
Internal Reasoning
FREE
Input Cache Read
FREE

Best Overall scoring LLMs

xAI

Grok 4 Fast

88
score
1st
placement
Qwen

Qwen3 VL 235B A22B Instruct

86
score
2nd
placement
xAI

Grok 4.1 Fast

84
score
3rd
placement
OpenAI

GPT-5.1 Chat

82
score
4th
placement
OpenAI

GPT-5.1-Codex

82
score
4th
placement
Anthropic

Claude Haiku 4.5

80
score
5th
placement