ModelCap
Current AI model comparison
Exact identities · public evidence
Z.ai
GLM 4.6V
Position
#122
Index
49.0
Measured
2 public benchmark observations across 2 boards
Comparison side 1
Z.ai
GLM 5 Turbo
Position
#109
Index
53.5
Measured
publisher-corpus-prior over 231 held-out anchors (63%); 1 specialist-board observation at 1.2% support (37%); shrunk 24.7 up toward the measured corpus
Comparison side 2
Output / 1M
$0.90
vs $4.00
Context
131K
vs 203K
Weights
Open weights
vs API only