Op
gpt-5-nano Benchmark & Insights
OpenAI OpenAI API
Updated Jul 18, 2026 All models
Sample size
157 runs
in window
Accuracy
69.4%
consensus match · 160d
Confidence
67%
over 162 runs
Window end
Jul 18, 2026
most recent run
Input price
$0.05/MTok
prompt tokens
Output price
$0.40/MTok
completion tokens
Model insights
- 01 At $0.05/$0.40 it is nearly free, and it behaves like it: 61 overratings vs 6 under, ~28 false "unsafe" alarms, and frequent solo jumps to "high" on "medium" days.
- 02 Usable only if you accept constant false alarms in exchange for almost never missing danger.
Recent forecasts