ModelCap

Current AI model comparison

Exact identities · public evidence

OpenAI

gpt oss safeguard 120b

Position

#141

Index

32.2

Inherited

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

Comparison side 1

Qwen

Qwen3 4B Instruct 2507

Position

#140

Index

32.4

Estimated

publisher-corpus-prior over 186 held-out anchors (19%); launch card against 2 resolved peers on 9 rows (81%); exceeds every named peer on 7 of 9 rows; no cross-lab optimism probe available; shrunk 4.1 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs 262K

Weights

Open weights

vs Open weights