ModelCap

Current AI model comparison

Exact identities · public evidence

OpenAI

gpt oss safeguard 120b

Position

#136

Index

34.9

Inherited

finetune of openai/gpt-oss-120b · fp4 (100%)

Comparison side 1

Tiiuae

Falcon H1 7B Instruct

Position

#135

Index

35.1

Estimated

global-corpus-prior over 195 held-out anchors (18%); launch card against 2 resolved peers on 11 rows (82%); exceeds every named peer on 7 of 11 rows; optimism haircut 0.14 from cross-lab-probe; shrunk 3.8 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Restricted license