ModelCap

Current AI model comparison

Exact identities · public evidence

Google

gemma 3n E2B it

Position

#162

Index

22.5

Inherited

finetune of google/gemma-3n-E4B-it · finetune (100%)

Comparison side 1

Google

gemma 4 E4B it

Position

#102

Index

42.5

Estimated

publisher-corpus-prior over 186 held-out anchors (7%); launch card against 3 resolved peers on 5 rows (93%); no cross-lab optimism probe available; shrunk 1.6 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Gated access

vs Open weights