ModelCap
Current AI model comparison
Exact identities · public evidence
Gemma 3 4B
Position
#151
Index
19.3
Measured
2 public benchmark observations across 2 boards
Comparison side 1
gemma 4 E4B it
Position
#101
Index
41.0
Estimated
publisher-corpus-prior over 183 held-out anchors (6%); launch card against 3 resolved peers on 5 rows (94%); no cross-lab optimism probe available; shrunk 1.6 up toward the measured corpus
Comparison side 2
Output / 1M
$0.10
vs Unavailable
Context
131K
vs —
Weights
Gated access
vs Open weights