Calvin Wankhede / Android Authority
TL;DR
- GPT-5 faced criticism for being curt and less personable, but OpenAI has improved its performance, personality, and limits.
- GPT-5 now has a few new modes for ChatGPT Plus: Auto, Fast, Thinking Mini, and Thinking Pro.
- Legacy models like GPT-4o, GPT-4.1, o3, and o4-mini are now available again for those who prefer them.
GPT-5 has faced a wave of criticism recently, both from everyday users and reviewers like our very own Calvin Wankhede here at Android Authority. Much of this feedback centered on the new model feeling more curt and having less personality. OpenAI responded quickly, addressing performance, personality, and usage limit issues — improving the overall experience significantly. Now, a fresh update makes things even better, at least for ChatGPT Plus subscribers.
Don’t want to miss the best from Android Authority?
OpenAI has greatly expanded GPT-5’s functionality by adding more modes: Auto, Fast, Thinking Mini, and Thinking Pro. Personally, I find GPT-5 better than most alternatives in certain scenarios, though your preference may vary. I tend to favor its concise, down-to-earth tone, which feels less sycophantic than GPT-4o.
Of course, not everyone agrees. If you still miss the old models or remain unimpressed with the latest upgrades, the good news is that several legacy models are once again available:
- GPT-4o: The previous default model, designed for general use.
- GPT-4.1: Slightly better for specific, detailed queries, though similar to 4o overall.
- o3: Formerly the go-to model for deeper questions, philosophical reflection, and more.
- o4-mini: A thinking model similar to o3 but better suited for simpler queries.
Honestly, I think this is a great move and makes it clear that OpenAI, at least, is trying to listen to its customers. While GPT-5 will continue to improve in the coming weeks and months, more models (and the flexibility they provide) isn’t a bad thing.
Thank you for being part of our community. Read our Comment Policy before posting.
