ModelCap

Current AI model comparison

Exact identities · public evidence

Kwaipilot

KAT Coder V2.5 Dev

Position

#34

Index

57.7

Estimated

start rank interpolated from the launch card's own comparison table against resolved catalogue peers, discounted for measured cross-lab optimism

Comparison side 1

Thinking Machines

Inkling Small

Position

#31

Index

58.9

Measured

2 public benchmark observations across 2 boards

Comparison side 2

Output / 1M

Unavailable

vs $1.20

Context

vs 524K

Weights

Open weights

vs Open weights