ModelCap
Current AI model comparison
Exact identities · public evidence
Nex AGI
Nex-N2.5-Pro
Position
#17
Index
76.3
Estimated
global-corpus-prior over 194 held-out anchors (9%); launch card against 8 resolved peers on 8 rows (92%); exceeds every named peer on 1 of 8 rows; optimism haircut 0 from cross-lab-probe; shrunk 2.3 toward the measured corpus
Comparison side 1
OpenAI
GPT-5.4 Mini
Position
#34
Index
66.3
Measured
4 public benchmark observations across 4 boards
Comparison side 2
Output / 1M
Free
vs $4.50
Context
262K
vs 400K
Weights
Open weights
vs API only