Model WarsApril 16, 2026via Reuters Technology

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

Why it matters

OpenAI's 'Thinking' mode represents a meaningful capability jump in reasoning tasks, directly competing with other reasoning-focused models. This benchmarks as a competitive differentiator in the model capability race.

Key signals

  • ChatGPT 'Thinking' mode achieves 94% reasoning score
  • Solves 7 prompt categories that standard ChatGPT cannot
  • Published April 16, 2026
  • Source: Tom's Guide

The hook

94%. That's ChatGPT's new reasoning score on its 'Thinking' mode — and it's solving problems standard AI can't touch.

ChatGPT’s new ‘Thinking’ mode just hit a 94% reasoning score — 7 prompts it can solve that standard AI can’t  Tom's Guide
Relevance score:78/100

Get stories like this every Friday.

The 5 AI stories that matter — free, in your inbox.

Free forever. No spam.