
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.