ModelCap

Current AI model comparison

Exact identities · public evidence

Google

gemma 4 12B it

Position

#45

Index

61.4

Estimated

publisher-corpus-prior over 183 held-out anchors (6%); launch card against 3 resolved peers on 6 rows (94%); no cross-lab optimism probe available; shrunk 0.2 up toward the measured corpus

Comparison side 1

Thinking Machines

Inkling

Position

#43

Index

62.9

Measured

5 public benchmark observations across 5 boards

Comparison side 2

Output / 1M

Unavailable

vs $4.05

Context

—

vs 1M

Weights

Open weights

vs Open weights