ModelCap
Current AI model comparison
Exact identities · public evidence
LGAI EXAONE
EXAONE 4.0.1 32B
Position
#127
Index
37.3
Estimated
global-corpus-prior over 193 held-out anchors (11%); launch card against 8 resolved peers on 8 rows (90%); optimism haircut 0 from cross-lab-probe; shrunk 1.7 up toward the measured corpus
Comparison side 1
OpenAI
GPT-4o-mini
Position
#131
Index
35.9
Measured
publisher-corpus-prior over 193 held-out anchors (61%); 1 specialist-board observation at 2.1% support (39%); shrunk 22.3 up toward the measured corpus
Comparison side 2
Output / 1M
Unavailable
vs $0.60
Context
—
vs 128K
Weights
Restricted license
vs API only