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

Moonshot AI

Kimi K2 Thinking

Position

#44

Index

62.2

Measured

2 public benchmark observations across 2 boards

Comparison side 2

Output / 1M

Unavailable

vs $2.50

Context

—

vs 262K

Weights

Open weights

vs Restricted license