ModelCap
Current AI model comparison
Exact identities · public evidence
Nex AGI
Nex N2.5 Max
Position
#13
Index
77.8
Estimated
global-corpus-prior over 182 held-out anchors (7%); launch card against 5 resolved peers on 5 rows (93%); optimism haircut 0 from cross-lab-probe; shrunk 1.8 toward the measured corpus
Comparison side 1
Z.ai
GLM 5.3
Position
#8
Index
82.1
Measured
4 public benchmark observations across 4 boards
Comparison side 2
Output / 1M
Unavailable
vs $4.40
Context
—
vs 1.3M
Weights
Open weights
vs Restricted license