ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen2.5 Omni 3B
Position
#203
Index
20.0
Estimated
publisher-corpus-prior over 215 held-out anchors (19%); launch card against 2 resolved peers on 5 rows (82%); exceeds every named peer on 1 of 5 rows; optimism haircut 2.4 from cross-lab-probe; shrunk 8.2 up toward the measured corpus
Comparison side 1
Zai Org
SWE Dev 32B
Position
#206
Index
19.6
Inherited
finetune of qwen/qwen-2.5-coder-32b-instruct · finetune (100%)
Comparison side 2
Output / 1M
Unavailable
vs Unavailable
Context
—
vs —
Weights
Restricted license
vs Open weights