ModelCap

Current AI model comparison

Exact identities · public evidence

Google

gemma 4 E2B it

Position

#112

Index

41.2

Estimated

publisher-corpus-prior over 194 held-out anchors (8%); launch card against 3 resolved peers on 5 rows (92%); no cross-lab optimism probe available; shrunk 2.1 up toward the measured corpus

Comparison side 1

Tiiuae

Falcon H1 34B Instruct

Position

#120

Index

39.8

Estimated

global-corpus-prior over 194 held-out anchors (49%); launch card against 5 resolved peers on 11 rows (51%); exceeds every named peer on 3 of 11 rows; optimism haircut 0 from cross-lab-probe; shrunk 12 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Restricted license