readable AI benchmarks (simplified)

readable AI benchmarks

KwaiKAT

KAT-Coder-Pro V1

non-reasoning · closed weights · Nov 11, 2025

KAT-Coder-Pro V1 has a Quality Score of 29.9, ranking 250th among 551 scored models. It has a 256k token context window. Its Reliability Score is 31.1, ranking 297th among 553 scored models, below average (total average: 35.6).

Quality Score29.9coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability31.1
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
256k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
not available
Output
not available
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
18.6
Coding
not available
Agentic
not available
Omniscience
-37.7
Correct
17.7%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 73.1%

Correct 17.7%Incorrect 55.4%Partial / not attempted 26.9%

Artificial Analysis benchmarks

GDPval-AA v2
11%
Humanity’s Last Exam
34%
GPQA Diamond
76%
CritPt
0%
AA-Omniscience
31%
AA-LCR
39%

Similar models

Support me! Patreon