ModelCap

Current AI model comparison

Exact identities · public evidence

Internlm

Intern S2 Preview 397B

Position

#105

Index

51.7

Measured

global-corpus-prior over 209 held-out anchors (63%); 1 specialist-board observation at 1.2% support (37%); shrunk 8.8 up toward the measured corpus

Comparison side 1

Nanbeige

Nanbeige4.1 3B

Position

#108

Index

49.2

Estimated

global-corpus-prior over 209 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 1.7 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Open weights