ModelCap
Current AI model comparison
Exact identities · public evidence
Nex AGI
Nex-N2.5-Mini
Position
#32
Index
67.6
Estimated
global-corpus-prior over 194 held-out anchors (16%); launch card against 6 resolved peers on 3 rows (84%); no cross-lab optimism probe available; shrunk 2.9 toward the measured corpus
Comparison side 1
Qwen
Qwen3.8 27B
Position
#35
Index
65.7
Measured
4 public benchmark observations across 4 boards
Comparison side 2
Output / 1M
Free
vs $2.55
Context
262K
vs 1M
Weights
Open weights
vs Open weights