ModelCap

Current AI model comparison

Exact identities · public evidence

NVIDIA

Nemotron Cascade 2 30B A3B

Position

#123

Index

36.3

Estimated

publisher-corpus-prior over 186 held-out anchors (58%); launch card against 3 resolved peers on 11 rows (42%); exceeds every named peer on 3 of 11 rows; optimism haircut 0 from cross-lab-probe; shrunk 3.3 up toward the measured corpus

Comparison side 1

OpenAI

GPT-4o-mini

Position

#126

Index

35.4

Measured

publisher-corpus-prior over 186 held-out anchors (61%); 1 specialist-board observation at 2.1% support (39%); shrunk 21.8 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs $0.60

Context

vs 128K

Weights

Restricted license

vs API only