ModelCap
Current AI model comparison
Exact identities · public evidence
Tencent
Hy4 preview
Position
#26
Index
73.5
Measured
9 reported rows against measured corpus ladders (41%); publisher-corpus-prior over 203 held-out anchors (11%); opens above measured predecessor tencent/hy3 on same-family ordering evidence (39%); 1 specialist-board observation at 2.5% support (9%); shrunk 1.1 toward the measured corpus
Comparison side 1
Xiaomi
MiMo-V2.6-Pro
Position
#5
Index
84.9
Measured
1 public benchmark observation across 1 board
Comparison side 2
Output / 1M
$2.50
vs $0.87
Context
1M
vs 1M
Weights
Open weights
vs API only