ModelCap

Current AI model comparison

Exact identities · public evidence

Nanbeige

Nanbeige4.1 3B

Position

#96

Index

43.9

Estimated

global-corpus-prior over 185 held-out anchors (19%); launch card against 2 resolved peers on 6 rows (81%); exceeds every named peer on 5 of 6 rows; optimism haircut 3 from cross-lab-probe; shrunk 2.3 up toward the measured corpus

Comparison side 1

Qwen

Qwen3 Coder 480B A35B

Position

#93

Index

46.4

Measured

2 public benchmark observations across 2 boards

Comparison side 2

Output / 1M

Unavailable

vs $1.00

Context

vs 262K

Weights

Open weights

vs Open weights