ModelCap

Current AI model comparison

Exact identities · public evidence

Nex AGI

Nex-N2.5-Pro

Position

#17

Index

75.8

Estimated

global-corpus-prior over 182 held-out anchors (12%); launch card against 7 resolved peers on 8 rows (88%); exceeds every named peer on 1 of 8 rows; optimism haircut 0 from cross-lab-probe; shrunk 3 toward the measured corpus

Comparison side 1

Xiaomi

MiMo-V2.5-Pro

Position

#21

Index

72.8

Measured

5 public benchmark observations across 5 boards

Comparison side 2

Output / 1M

Free

vs $0.87

Context

262K

vs 1M

Weights

Open weights

vs Open weights