Op
gpt-5.4-mini Benchmark & Insights
OpenAI OpenAI API
Updated Jul 31, 2026 All models
Sample size
170 runs
in window
Accuracy
70.1%
consensus match · 177d
Confidence
94%
over 179 runs
Window end
Jul 31, 2026
most recent run
Input price
$0.75/MTok
prompt tokens
Output price
$4.50/MTok
completion tokens
Model insights
- 01 Fifty-seven upward misses and zero downward, plus a long tail of "unsafe" calls on "safe" days: wrong in one direction, constantly.
- 02 It lands well below both the older GPT-5-mini and the full GPT-5.4, so this mini tier is a clear regression.
Recent forecasts