ModelCap
Current AI model comparison
Exact identities · public evidence
OpenAI
GPT-5.5 Pro
Position
#55
Index
58.6
Measured
publisher-corpus-prior over 188 held-out anchors (61%); 1 specialist-board observation at 2.1% support (39%); shrunk 14.1 toward the measured corpus
Comparison side 1
OpenAI
gpt oss safeguard 120b
Position
#143
Index
32.3
Inherited
finetune of openai/gpt-oss-120b · fp4 (100%)
Comparison side 2
Output / 1M
$180
vs Unavailable
Context
1M
vs —
Weights
API only
vs Open weights