ModelCap

Current AI model comparison

Exact identities · public evidence

IBM Granite

granite guardian 4.1 8b

Position

#182

Index

23.5

Inherited

finetune of ibm-granite/granite-4.1-8b · finetune (100%)

Comparison side 1

LiquidAI

LFM2 8B A1B

Position

#188

Index

20.4

Estimated

global-corpus-prior over 203 held-out anchors (19%); launch card against 3 resolved peers on 10 rows (82%); exceeds every named peer on 8 of 10 rows; optimism haircut 9.5 from cross-lab-probe; shrunk 7.8 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Restricted license