ModelCap
Current AI model comparison
Exact identities · public evidence
Qwen
Qwen3.6 35B A3B
Position
#74
Index
50.7
Estimated
publisher-corpus-prior over 183 held-out anchors (13%); opens above measured predecessor qwen/qwen3.5-35b-a3b on same-family ordering evidence (46%); launch card against 4 resolved peers on 10 rows (41%); exceeds every named peer on 2 of 10 rows; optimism haircut 0 from cross-lab-probe; shrunk 0.1 toward the measured corpus
Comparison side 1
Tencent
UI Mate democua 27B
Position
#71
Index
52.8
Inherited
finetune of qwen/qwen3.6-27b · finetune (100%)
Comparison side 2
Output / 1M
$0.90
vs Unavailable
Context
262K
vs —
Weights
Open weights
vs Open weights