ModelCap

Current AI model comparison

Exact identities · public evidence

Deep Cogito

cogito v2 preview llama 70B

Position

#195

Index

22.5

Inherited

finetune of meta-llama/Llama-3.1-70B · finetune (100%)

Comparison side 1

LiquidAI

LFM2 8B A1B

Position

#190

Index

23.1

Estimated

global-corpus-prior over 215 held-out anchors (18%); 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 7.5 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Restricted license

vs Restricted license