ModelCap
Current AI model comparison
Exact identities · public evidence
Meta
Llama 4 Scout
Position
#162
Index
27.0
Measured
4 public benchmark observations across 4 boards
Comparison side 1
Tiiuae
Falcon H1R 7B
Position
#158
Index
29.7
Estimated
global-corpus-prior over 194 held-out anchors (9%); launch card against 2 resolved peers on 7 rows (91%); exceeds every named peer on 1 of 7 rows; optimism haircut 2.2 from cross-lab-probe; shrunk 2.2 up toward the measured corpus
Comparison side 2
Output / 1M
$0.30
vs Unavailable
Context
1.3M
vs —
Weights
Gated access
vs Restricted license