ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen3 Coder 30B A3B Instruct
Position
#119
Index
53.4
Estimated
publisher-corpus-prior over 232 held-out anchors (7%); launch card against 3 resolved peers on 4 rows (94%); no cross-lab optimism probe available
Comparison side 1
Qwen
Qwen3 VL 8B Instruct
Position
#208
Index
34.6
Estimated
3 reported rows against measured corpus ladders (63%); publisher-corpus-prior over 232 held-out anchors (38%); shrunk 11.4 up toward the measured corpus
Comparison side 2
Output / 1M
$0.28
vs $0.455
Context
262K
vs 262K
Weights
Open weights
vs Open weights