ModelCap

Current AI model comparison

Exact identities · public evidence

Kuaishou

KAT-Coder-Pro V2.5

Position

#61

Index

43.3

Estimated

start rank inherited from the measured predecessor in its own product family, less a fixed succession penalty, until independent measurements replace it

Comparison side 1

OpenAI

o4 Mini

Position

#62

Index

43.2

Measured

4 public benchmark observations across 4 boards

Comparison side 2

Output / 1M

$2.96

vs $4.40

Context

262K

vs 200K

Weights

API only

vs API only