KAT-Coder-Pro V2
KwaiPilot · released Mar 27, 2026
KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...
Specification
- Context window
- 262K
- Max output
- 80K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 2
- Moderated
- No
- Uptime
- 100.0%
Intelligence
33.9
79th percentile
Coding
59.5
Coding Index
Agentic
—
Agentic Index
Output speed
46 t/s
Median across providers
Latency
760ms
Time to first token
Cost per task
$0.04
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- τ²-bench (Telecom)89.5%
- GPQA Diamond85.5%
- AA-LCR (long context)70.0%
- IFBench66.7%
- Terminal-Bench Hard49.2%
- SciCode38.3%
- Humanity's Last Exam16.1%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 89.5% |
| GPQA Diamond | 85.5% |
| AA-LCR (long context) | 70.0% |
| IFBench | 66.7% |
| Terminal-Bench Hard | 49.2% |
| SciCode | 38.3% |
| Humanity's Last Exam | 16.1% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- M2.5MiniMax34.5
- GLM 4.7Z.ai34.5
- Hy3 previewTencent34.4
- 34.3
- KAT-Coder-Pro V2KwaiPilot33.9
- LongCat 2.0Meituan33.9
- Kimi K2 ThinkingMoonshot AI33.5
- o3 ProOpenAI33.3
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| M2.5 | 34.5 |
| GLM 4.7 | 34.5 |
| Hy3 preview | 34.4 |
| Qwen3.5 397B A17B | 34.3 |
| KAT-Coder-Pro V2 | 33.9 |
| LongCat 2.0 | 33.9 |
| Kimi K2 Thinking | 33.5 |
| o3 Pro | 33.3 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.3
- Output / 1M tokens
- $1.2
- Cached input / 1M
- $0.06
- Blended 3:1
- $0.525
One task, estimated
$0.04
- Input tokens
- 50,000
- Output tokens
- 25,000
- Profile
- Standard
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.