gpt-5.4-nano Benchmark & Insights

OpenAI OpenAI API

Updated Jul 31, 2026 All models

Sample size

172 runs

in window

Accuracy

44.4%

consensus match · 178d

Confidence

70%

over 182 runs

Window end

Jul 31, 2026

most recent run

Input price

$0.20/MTok

prompt tokens

Output price

$1.25/MTok

completion tokens

Model insights

01 Last place and the most extreme pessimist in the set: 146 upward misses, none downward, and forty-nine "high" calls against a consensus that saw ten.
02 It disagrees with the panel more often than it agrees, so however cheap it is, its output carries no signal.

Recent forecasts

Date

Conf.

Risk

Safe