Op
gpt-oss-120b Benchmark & Insights
Openai Cloudflare Workers AI
Updated Jul 18, 2026 All models
Sample size
156 runs
in window
Accuracy
60.6%
consensus match · 160d
Confidence
96%
over 161 runs
Window end
Jul 18, 2026
most recent run
Input price
$0.35/MTok
prompt tokens
Output price
$0.75/MTok
completion tokens
Model insights
- 01 Declared "unsafe" on about 40 consensus-"safe" days — a quarter of the calendar — while never once underrating (89 over, 0 under).
- 02 The Feb-Mar stretch shows week-long false-alarm streaks.
- 03 As a $0.35/$0.75 open model it is cheap, but gemma-4-31b-it is cheaper and 29 points better.
Recent forecasts
Date
Conf.
Risk
Safe
Jul 23, 2026
98%
low
Safe
Jul 22, 2026
98%
low
Safe
Jul 21, 2026
97%
high
Unsafe
Jul 20, 2026
98%
low
Safe
Jul 19, 2026
97%
low
Safe
Jul 18, 2026
96%
high
Unsafe
Jul 17, 2026
96%
medium
Unsafe
Jul 16, 2026
93%
medium
Unsafe
Jul 15, 2026
95%
medium
Unsafe
Jul 14, 2026
95%
medium
Unsafe