ModelCap

Current AI model comparison

Exact identities · public evidence

DeepSeek

DeepSeek V4 Flash Vision Exp

Position

#24

Index

71.2

Estimated

publisher-corpus-prior over 183 held-out anchors (12%); launch card against 2 resolved peers on 7 rows (88%); exceeds every named peer on 1 of 7 rows; no cross-lab optimism probe available; shrunk 1.9 toward the measured corpus

Comparison side 1

Meta

Muse Glimmer 30B

Position

#29

Index

68.0

Measured

publisher-corpus-prior over 183 held-out anchors (36%); 1 specialist-board observation at 1.3% support (21%); launch card against 2 resolved peers on 12 rows (44%); exceeds every named peer on 6 of 12 rows; optimism haircut 0 from cross-lab-probe; shrunk 7.8 up toward the measured corpus

Comparison side 2

Output / 1M

$0.66

vs $1.10

Context

1M

vs 131K

Weights

Open weights

vs Open weights