Qw
qwen3-30b-a3b-fp8
Benchmark & Insights
Qwen Cloudflare Workers AI
Updated Oct 4, 2026 All models
Sample size
232 runs
in window
Accuracy
56.2%
reference match · 251d
Confidence
92%
over 252 runs
Window end
Oct 4, 2026
most recent run
Input price
$0.05/MTok
prompt tokens
Output price
$0.34/MTok
completion tokens
Model insights
- 01 Strongly pessimistic: it rated risk too high on 70 days and too low on just 6.
- 02 It called 43 "LOW" days "medium" and 51 safe days "unsafe".
- 03 Its few missed days come from over-warning, not skill.
Recent forecasts