Op
gpt-5.6-sol
Benchmark & Insights
OpenAI OpenAI API
Updated Oct 4, 2026 All models
Sample size
232 runs
in window
Accuracy
78.4%
reference match · 241d
Confidence
90%
over 243 runs
Window end
Oct 4, 2026
most recent run
Input price
$4.00/MTok
prompt tokens
Output price
$20.00/MTok
completion tokens
Model insights
- 01 Near the top, beating 33 of 35 same-day peers with zero false alarms.
- 02 Its lean high is mild: it rates some "LOW" days "medium" but never calls a safe day "unsafe".
- 03 Costs twice as much as gpt-6.1-sol ($4/$20) for slightly worse results.