ModelCap

Current AI model comparison

Exact identities · public evidence

Stepfun Ai

Step3 VL 10B

Position

#57

Index

60.9

Estimated

global-corpus-prior over 195 held-out anchors (21%); launch card against 2 resolved peers on 4 rows (79%); exceeds every named peer on 3 of 4 rows; no cross-lab optimism probe available; shrunk 2.2 toward the measured corpus

Comparison side 1

XingChen AGI

Xing4.0 29B A4B

Position

#56

Index

60.9

Estimated

global-corpus-prior over 195 held-out anchors (9%); launch card against 2 resolved peers on 5 rows (91%); exceeds every named peer on 1 of 5 rows; optimism haircut 0 from cross-lab-probe; shrunk 0.8 toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Open weights