Zh
glm-4.7-flash Benchmark & Insights
Zhipu AI Cloudflare Workers AI
Updated Jun 6, 2026 All models
Sample size
42 runs
in window
Accuracy
79.5%
consensus match · 44d
Confidence
98%
over 44 runs
Window end
Jun 6, 2026
most recent run
Input price
$0.06/MTok
prompt tokens
Output price
$0.40/MTok
completion tokens
Model insights
- 01 The heaviest false-alarm machine: 8 of its 9 divergent days include an "unsafe" call against a consensus "safe", giving it the worst safe-agreement on the board, nearly all clustered in May.
- 02 Ultra-cheap at $0.06/$0.40, but a third of its "unsafe" warnings can't be trusted.
Recent forecasts