ModelCap

Current AI model comparison

Exact identities · public evidence

Anthropic

Claude Haiku 4.5

Position

#70

Index

56.4

Measured

3 public benchmark observations across 3 boards

Comparison side 1

Internlm

Intern S2 Preview

Position

#73

Index

55.8

Estimated

4 reported rows against measured corpus ladders (32%); global-corpus-prior over 195 held-out anchors (68%); shrunk 6.5 toward the measured corpus

Comparison side 2

Output / 1M

$5.00

vs Unavailable

Context

200K

vs —

Weights

API only

vs Open weights