ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen3.5 0.8B
Position
#212
Index
34.5
Estimated
6 reported rows against measured corpus ladders (58%); publisher-corpus-prior over 231 held-out anchors (42%); shrunk 14 up toward the measured corpus
Comparison side 1
Qwen
Qwen3.5 4B
Position
#153
Index
44.0
Estimated
publisher-corpus-prior over 231 held-out anchors (13%); launch card against 4 resolved peers on 11 rows (87%); optimism haircut 0.6 from cross-lab-probe; shrunk 1.5 up toward the measured corpus
Comparison side 2
Output / 1M
Unavailable
vs Unavailable
Context
—
vs —
Weights
Open weights
vs Open weights