ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen Image Bench
Position
#64
Index
60.1
Inherited
finetune of qwen/qwen3.6-27b · finetune (100%)
Comparison side 1
Qwen
Qwen2.5 Omni 7B
Position
#184
Index
21.3
Estimated
publisher-corpus-prior over 203 held-out anchors (24%); launch card against 2 resolved peers on 5 rows (76%); exceeds every named peer on 2 of 5 rows; optimism haircut 2.4 from cross-lab-probe; shrunk 10.1 up toward the measured corpus
Comparison side 2
Output / 1M
Unavailable
vs Unavailable
Context
—
vs —
Weights
Open weights
vs Restricted license