readable AI benchmarks

KwaiKAT

KAT Coder Pro V2

non-reasoning · closed weights · Mar 27, 2026

Quality Score33.7
Value Score32.0
Reliability38.8
Cache Discount80%

Model specification

Reasoning
non-reasoning
Input modalities
text
Output modalities
text
Context window
256k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.300
Output
$1.20
Cached Input
$0.060
Cached Output
not available
Cost per task
not available

Capability

Intelligence
33.7
Coding
59.5
Agentic
15.1
Omniscience
-22.5
Correct
21.5%
Blended price
$0.222

Answer outcomes

Correct 21.5%Incorrect 44.0%Abstained 34.6%

Artificial Analysis benchmarks

GDPval-AA v2
20%
τ³-Banking
5%
Terminal-Bench v2.1
70%
SciCode
38%
Humanity’s Last Exam
16%
GPQA Diamond
85%
CritPt
0%
AA-Omniscience
39%
AA-LCR
70%

Similar models