ModelCap

Current AI model comparison

Exact identities · public evidence

DeepSeek

DeepSeek V4.1 Flash

Position

#16

Index

76.5

Measured

1 public benchmark observation across 1 board

Comparison side 1

Ornith Ai

Ornith 1.5 397B

Position

#18

Index

75.6

Estimated

global-corpus-prior over 186 held-out anchors (11%); launch card against 2 resolved peers on 11 rows (89%); exceeds every named peer on 3 of 11 rows; optimism haircut 0 from cross-lab-probe; shrunk 2.8 toward the measured corpus

Comparison side 2

Output / 1M

$0.60

vs Unavailable

Context

1M

vs

Weights

Open weights

vs Open weights