ModelCap

Current AI model comparison

Exact identities · public evidence

DeepSeek

DeepSeek V4 Flash 0731

Position

#25

Index

70.7

Measured

2 public benchmark observations across 2 boards

Comparison side 1

Nex AGI

Nex-N2.5-Pro

Position

#10

Index

79.1

Estimated

global-corpus-prior over 183 held-out anchors (11%); launch card against 6 resolved peers on 3 rows (89%); exceeds every named peer on 1 of 3 rows; no cross-lab optimism probe available; shrunk 3.1 toward the measured corpus

Comparison side 2

Output / 1M

$0.18

vs Free

Context

1.3M

vs 262K

Weights

Open weights

vs Open weights