ModelCap

Current AI model comparison

Exact identities · public evidence

Poolside

Laguna S 2.1

Position

#46

Index

62.3

Estimated

5 reported rows against measured corpus ladders (66%); global-corpus-prior over 193 held-out anchors (34%); shrunk 5.3 toward the measured corpus

Comparison side 1

XiaomiMiMo

MiMo V2 Flash

Position

#48

Index

61.4

Estimated

global-corpus-prior over 193 held-out anchors (14%); launch card against 4 resolved peers on 10 rows (86%); exceeds every named peer on 1 of 10 rows; optimism haircut 0 from cross-lab-probe; shrunk 1.6 toward the measured corpus

Comparison side 2

Output / 1M

$0.18

vs Unavailable

Context

1M

vs

Weights

Restricted license

vs Open weights