Back

KwaiKAT

KAT Coder Pro V2

Closed weights
Intelligence
21.7
Rank 223 of 744 measured models
Coding
59.5
Rank 86 of 298 measured models
Price/1M
$0.525
Rank 283 of 659 measured models
Context window
256K
Rank 518 of 1199 measured models

KAT Coder Pro V2 scores 21.7 on the Artificial Analysis Intelligence Index, ranking 223rd of 744 measured models. The closest models on this index are o3-pro (21.9), G9v3-39A5B (21.8), and MiMo-V2.5 (21.8). At $0.525 per million tokens (3:1 input/output blended price), it is cheaper than o3-pro ($35), more expensive than MiMo-V2.5 ($0.175).

Artificial Analysis Indices
Intelligence21.7
Rank 223 of 744 measured models
Coding59.5
Rank 86 of 298 measured models
Standard Benchmarks
GPQA Diamond85.5%
Rank 132 of 619 measured models
HLE16.1%
Rank 250 of 664 measured models
IFBench66.7%
Rank 93 of 450 measured models
AA-LCR73.0%
Rank 185 of 575 measured models
TerminalBench Hard49.2%
Rank 24 of 432 measured models
Terminal-Bench 2.170.0%
Rank 74 of 244 measured models
τ²-Bench89.5%
Rank 71 of 440 measured models
τ-Bench Banking4.5%
Rank 197 of 211 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