ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen3 Coder 30B A3B Instruct
Position
#107
Index
53.4
Estimated
publisher-corpus-prior over 211 held-out anchors (6%); launch card against 3 resolved peers on 4 rows (94%); no cross-lab optimism probe available; shrunk 0.1 toward the measured corpus
Comparison side 1
Qwen
Qwen3 VL 32B Instruct
Position
#154
Index
41.7
Estimated
4 reported rows against measured corpus ladders (51%); publisher-corpus-prior over 211 held-out anchors (50%); shrunk 9.8 up toward the measured corpus
Comparison side 2
Output / 1M
$0.28
vs Unavailable
Context
262K
vs 131K
Weights
Open weights
vs Open weights