ModelCap

Current AI model comparison

Exact identities · public evidence

Nex AGI

Nex-N2.5-Mini

Position

#30

Index

70.7

Estimated

global-corpus-prior over 203 held-out anchors (12%); launch card against 6 resolved peers on 3 rows (88%); no cross-lab optimism probe available; shrunk 2.1 toward the measured corpus

Comparison side 1

xAI

Grok 4.7

Position

#4

Index

85.0

Measured

1 public benchmark observation across 1 board

Comparison side 2

Output / 1M

Free

vs $4.80

Context

262K

vs 500K

Weights

Open weights

vs API only