Get all your news in one place.
100's of premium titles.
One app.
Start reading
Tom’s Guide
Tom’s Guide
Technology
Amanda Caswell

ChatGPT’s new ‘Thinking’ mode just hit a 94% reasoning score — 7 prompts it can solve that standard AI can’t

Human vs. robot face with ChatGPT on phone.

OpenAI recently updated GPT-5.4 with a feature that has the tech world buzzing: Extended Thinking mode. While the base model is already lightning-fast, this new toggle allows the AI to "ruminate"—running internal simulations and self-correcting before it ever types a single word of its response.

The results are a staggering 94% success rate on the ARC-AGI-1 reasoning benchmark, finally surpassing the 92.8% score held by human experts in the same category.

Sign up to read this article
Read news from 100's of titles, curated specifically for you.
Already a member? Sign in here
Related Stories
Top stories on inkl right now
One subscription that gives you access to news from hundreds of sites
Already a member? Sign in here
Our Picks
Fourteen days free
Download the app
One app. One membership.
100+ trusted global sources.