Gemini 2.5 Pro June and even the newest Gemini 2.5 Flash September release both are considerably less verbose in their outputs, its like they have an internal limit for output tokens. I feel its needs a verbosity selector option to adjust how verbose the model is, I understand some users don’t prefer longer responses but Gemini 2.5 pro 03-25 was amazing because it was so accurate and verbose….The current models just don’t output enough text to deeply critique my work and make their point, even when asked to be provide a detailed explanation.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Gemini 2.5 Update Feedback: Reduced Depth in Processing & Overly Polite Tone Compared to Previous Version | 2 | 448 | May 8, 2025 | |
| Gemini 2.5 Pro is disappointing | 0 | 118 | September 5, 2025 | |
| Gemini 1.5 pro does not want to write code at full capacity using all its tokens. instead, he shortens the code with comments, which is not the case in gemini 2.0 | 3 | 271 | January 21, 2025 | |
| Gemini Flash 2.0 is useless? | 5 | 1219 | December 23, 2024 | |
| Gemini 2.0 Pro Experimental 02-05 is having formatting issues | 1 | 279 | May 19, 2025 |