ModelCap

Current AI model comparison

Exact identities · public evidence

Qwen

Qwen3.5 4B

Position

#141

Index

43.1

Estimated

publisher-corpus-prior over 210 held-out anchors (29%); launch card against 3 resolved peers on 10 rows (71%); exceeds every named peer on 2 of 10 rows; optimism haircut 0.6 from cross-lab-probe; shrunk 3.7 up toward the measured corpus

Comparison side 1

Qwen

Qwen3 VL 4B Instruct

Position

#206

Index

32.3

Estimated

3 reported rows against measured corpus ladders (61%); publisher-corpus-prior over 210 held-out anchors (39%); shrunk 12.5 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

—

vs —

Weights

Open weights

vs Open weights