ModelCap

Current AI model comparison

Exact identities · public evidence

Internlm

Intern S2 Preview

Position

#52

Index

59.4

Estimated

5 reported rows against measured corpus ladders (49%); global-corpus-prior over 187 held-out anchors (51%); shrunk 7.9 toward the measured corpus

Comparison side 1

Stepfun Ai

Step3 VL 10B

Position

#53

Index

58.6

Estimated

global-corpus-prior over 187 held-out anchors (19%); launch card against 2 resolved peers on 4 rows (81%); exceeds every named peer on 3 of 4 rows; no cross-lab optimism probe available; shrunk 1.6 toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Open weights