ModelCap
Current AI model comparison
Exact identities · public evidence
Meta
Muse Spark Open
Position
#14
Index
79.8
Estimated
publisher-corpus-prior over 210 held-out anchors (21%); launch card against 5 resolved peers on 11 rows (79%); exceeds every named peer on 3 of 11 rows; optimism haircut 0 from cross-lab-probe; shrunk 0.8 up toward the measured corpus
Comparison side 1
MiniMaxAI
MiniMax M3.1 Flash
Position
#22
Index
77.7
Estimated
global-corpus-prior over 210 held-out anchors (6%); launch card against 5 resolved peers on 6 rows (94%); optimism haircut 0 from cross-lab-probe; shrunk 1.8 toward the measured corpus
Comparison side 2
Output / 1M
$4.25
vs Unavailable
Context
1M
vs —
Weights
Gated access
vs Restricted license