ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen3.5 2B
Position
#151
Index
41.3
Estimated
7 reported rows against measured corpus ladders (51%); publisher-corpus-prior over 210 held-out anchors (50%); shrunk 9 up toward the measured corpus
Comparison side 1
Qwen
Qwen3 Omni 30B A3B Instruct
Position
#119
Index
49.3
Estimated
publisher-corpus-prior over 210 held-out anchors (9%); launch card against 4 resolved peers on 5 rows (91%); exceeds every named peer on 1 of 5 rows; no cross-lab optimism probe available; shrunk 0.1 up toward the measured corpus
Comparison side 2
Output / 1M
Unavailable
vs Unavailable
Context
—
vs —
Weights
Open weights
vs Restricted license