ModelCap
Current AI model comparison
Exact identities · public evidence
Tencent
Hy-MT2-30B-A3B
Position
#73
Index
38.9
Estimated
publisher corpus prior · leave-one-anchor-out calibrated
Comparison side 1
Tencent
Hy4 preview
Position
#19
Index
68.6
Estimated
placed against measured peers on publisher-reported benchmarks, discounted for self-report optimism; floored directly above its measured family predecessor
Comparison side 2
Output / 1M
$0.295
vs $2.50
Context
8K
vs 1M
Weights
Open weights
vs Open weights