Op
gpt-oss-120b
Benchmark & Insights
Openai Cloudflare Workers AI
Updated Oct 4, 2026 All models
Sample size
232 runs
in window
Accuracy
57.0%
reference match · 251d
Confidence
95%
over 252 runs
Window end
Oct 4, 2026
most recent run
Input price
$0.35/MTok
prompt tokens
Output price
$0.75/MTok
completion tokens
Model insights
- 01 The second-most alarmist model: it called 51 of 76 "MEDIUM_SAFE" days "unsafe".
- 02 Its 3 misses come from flagging nearly everything.
- 03 Fell to 39% in July but improved to 77% in September.
Recent forecasts