Back

KwaiKAT

KAT-Coder-Pro V1

Closed weights
Intelligence
18.6
Rank 263 of 744 measured models
Context window
256K
Rank 518 of 1199 measured models

KAT-Coder-Pro V1 scores 18.6 on the Artificial Analysis Intelligence Index, ranking 263rd of 744 measured models. The closest models on this index are JT-35B-Flash (18.7), Claude 4.1 Opus (18.6), and MiniMax-M2 (18.6).

Artificial Analysis Indices
Intelligence18.6
Rank 263 of 744 measured models
Math94.7
Rank 10 of 270 measured models
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Economics27.1
Rank 162 of 225 measured models
Standard Benchmarks
MMLU Pro81.3%
Rank 91 of 349 measured models
GPQA Diamond76.4%
Rank 250 of 619 measured models
HLE33.6%
Rank 132 of 664 measured models
LiveCodeBench74.7%
Rank 48 of 343 measured models
AIME 202594.7%
Rank 10 of 270 measured models
IFBench68.4%
Rank 82 of 450 measured models
AA-LCR38.7%
Rank 377 of 575 measured models
TerminalBench Hard9.1%
Rank 245 of 432 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy