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

Tencent

UI Mate 9B

Position

#106

Index

39.9

Inherited

finetune of qwen/qwen3.5-9b · finetune (100%)

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

—

vs —

Weights

Open weights

vs Open weights