ModelCap

Current AI model comparison

Exact identities · public evidence

Google

gemma 4 E2B it

Position

#109

Index

39.2

Estimated

publisher-corpus-prior over 183 held-out anchors (9%); launch card against 3 resolved peers on 5 rows (91%); no cross-lab optimism probe available; shrunk 2.6 up toward the measured corpus

Comparison side 1

Qwen

Qwen3.5 4B

Position

#112

Index

38.3

Estimated

publisher-corpus-prior over 183 held-out anchors (26%); launch card against 3 resolved peers on 10 rows (74%); exceeds every named peer on 2 of 10 rows; optimism haircut 0.6 from cross-lab-probe; shrunk 4 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Open weights