Op

gpt-5.4 Benchmark & Insights

OpenAI OpenAI API
Updated Jul 31, 2026 All models
Sample size
170 runs
in window
Accuracy
80.7%
consensus match · 176d
Confidence
90%
over 178 runs
Window end
Jul 31, 2026
most recent run
Input price
$2.50/MTok
prompt tokens
Output price
$15.00/MTok
completion tokens
Model insights
  • 01 Never once underrated a day — all thirty-five misses are upgrades, usually "medium" over "low".
  • 02 Nine of them also flipped the flag to "unsafe" on a "safe" day, making it the mid-priced GPT that cries wolf.
Notes

Breakpoint pricing at 272K tokens (doubles to $5/$22.50 above threshold)

Recent forecasts