ModelCap

Current AI model comparison

Exact identities · public evidence

Google

gemma 4 12B it

Position

#52

Index

66.7

Estimated

publisher-corpus-prior over 209 held-out anchors (6%); launch card against 3 resolved peers on 6 rows (94%); no cross-lab optimism probe available

Comparison side 1

Stepfun Ai

Step3 VL 10B

Position

#55

Index

65.6

Estimated

global-corpus-prior over 209 held-out anchors (17%); launch card against 2 resolved peers on 4 rows (83%); exceeds every named peer on 3 of 4 rows; no cross-lab optimism probe available; shrunk 1.8 toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Open weights