ModelCap

Current AI model comparison

Exact identities · public evidence

Mistral AI

Mistral Small 4

Position

#117

Index

40.7

Measured

1 public benchmark observation across 1 board

Comparison side 1

Tiiuae

Falcon H1 34B Instruct

Position

#120

Index

39.8

Estimated

global-corpus-prior over 194 held-out anchors (49%); launch card against 5 resolved peers on 11 rows (51%); exceeds every named peer on 3 of 11 rows; optimism haircut 0 from cross-lab-probe; shrunk 12 up toward the measured corpus

Comparison side 2

Output / 1M

$0.60

vs Unavailable

Context

262K

vs

Weights

Open weights

vs Restricted license