ModelCap
Current AI model comparison
Exact identities · public evidence
Tencent
HiLS Attention 7B
Position
#212
Index
9.0
Inherited
finetune of allenai/Olmo-3-1025-7B · finetune (100%)
Comparison side 1
Tencent
Hy4 preview
Position
#26
Index
70.3
Measured
9 reported rows against measured corpus ladders (38%); publisher-corpus-prior over 194 held-out anchors (12%); opens above measured predecessor tencent/hy3 on same-family ordering evidence (41%); 1 specialist-board observation at 2.5% support (9%); shrunk 1.2 toward the measured corpus
Comparison side 2
Output / 1M
Unavailable
vs $2.50
Context
—
vs 1M
Weights
Open weights
vs Open weights