Z AI
GLM-4.5Open weights
Released 2025-07-28 · Context 131K · Data snapshot 2026-10-26
Overall score
54.6
Awaiting benchmarks (insufficient coverage)Benchmark coverage
15.4%
4 third-party benchmarks
Context window
131K
tokens
Input price
$0.60
Cache read $0.11
Output price
$2.20
per million tokens
OpenRouter usage
#290
1.2B tokens/day
Prices converted at snapshot-day rate (USD/CNY 6.6702)
Dimension performance
Human preference
59.8
Office
53.4
Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation
Benchmark details
Office2 items
Tax Eval v272.4
Corporate Finance v260.96
Knowledge1 items
MMLU-Pro81.22
Human preference1 items
LMArena Human Blind Vote1410.924
Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.