ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen2.5 VL 32B Instruct
Position
#118
Index
40.9
Estimated
publisher-corpus-prior over 197 held-out anchors (17%); launch card against 2 resolved peers on 4 rows (83%); exceeds every named peer on 2 of 4 rows; optimism haircut 0 from cross-lab-probe; shrunk 2 up toward the measured corpus
Comparison side 1
Qwen
Qwen3 Coder Next
Position
#121
Index
39.4
Measured
1 public benchmark observation across 1 board
Comparison side 2
Output / 1M
Unavailable
vs $0.80
Context
—
vs 262K
Weights
Open weights
vs Open weights