ModelCap

Current AI model comparison

Exact identities · public evidence

Internlm

Intern S2 Preview 397B

Position

#92

Index

48.5

Measured

global-corpus-prior over 197 held-out anchors (64%); 1 specialist-board observation at 1.3% support (36%); shrunk 5 up toward the measured corpus

Comparison side 1

Qwen

Qwen3 Omni 30B A3B Instruct

Position

#91

Index

48.7

Estimated

publisher-corpus-prior over 197 held-out anchors (10%); launch card against 4 resolved peers on 4 rows (90%); exceeds every named peer on 1 of 4 rows; no cross-lab optimism probe available; shrunk 0.2 up toward the measured corpus

Comparison side 2

Output / 1M

Unavailable

vs Unavailable

Context

vs

Weights

Open weights

vs Restricted license