ModelCap
Current AI model comparison
Exact identities · public evidence
gemma 4 12B it
Position
#47
Index
60.5
Estimated
publisher-corpus-prior over 186 held-out anchors (7%); launch card against 3 resolved peers on 6 rows (93%); no cross-lab optimism probe available; shrunk 0.2 up toward the measured corpus
Comparison side 1
Poolside
Laguna S 2.1
Position
#44
Index
62.2
Estimated
5 reported rows against measured corpus ladders (68%); global-corpus-prior over 186 held-out anchors (32%); shrunk 4.9 toward the measured corpus
Comparison side 2
Output / 1M
Unavailable
vs $0.18
Context
—
vs 1M
Weights
Open weights
vs Restricted license