As the heading suggest, I have been using Gemini Pro 3.0 since its launch. But the performance is very poor to say the least. The context window says its 1m but the chat forget things after 32k. Logic mistakes and recalling mistakes are ruining the experience. It just started to happen recently. Will it be fixed or is it just me who feels this way?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| The performance of Gemini 2.5 Pro has significantly decreased! | 11 | 2244 | October 17, 2025 | |
| Deterioration of the quality of the model's reasoning | 2 | 133 | January 23, 2026 | |
| Gemini 3 significantly worse thant 2.5 Pro at long context. Temperature likely to blame | 16 | 2505 | February 17, 2026 | |
| New Model Levels (Fast/Thinking/Pro) Continue to Be a Problem for Long Term Projects | 9 | 3801 | January 8, 2026 | |
| Gemini 2.5 Pro's Response Quality Regression | 9 | 1293 | September 15, 2025 |