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