ModelCap

Current AI model comparison

Exact identities · public evidence

AI21 Labs

Jamba Large 1.7

Position

#115

Index

21.4

Estimated

global corpus prior · leave-one-anchor-out calibrated

Comparison side 1

Google

Gemma 3 12B

Position

#177

Index

20.3

Measured

3 public benchmark observations across 3 boards

Comparison side 2

Output / 1M

$8.00

vs $0.15

Context

256K

vs 131K

Weights

Gated access

vs Gated access