ModelCap

Current AI model comparison

Exact identities · public evidence

Moonshot AI

Kimi K3.1 Pro

Position

#21

Index

78.6

Estimated

1 reported rows against measured corpus ladders (61%); publisher-corpus-prior over 211 held-out anchors (39%); shrunk 4 toward the measured corpus

Comparison side 1

Z.ai

GLM 5.3 Flash

Position

#24

Index

77.3

Measured

4 public benchmark observations across 4 boards

Comparison side 2

Output / 1M

$10.00

vs $0.50

Context

1M

vs 1M

Weights

No linked weights

vs Open weights