Gemini 3 significantly worse thant 2.5 Pro at long context. Temperature likely to blame

[MBB]

No, unfortunately, it seems like it’s somewhat ‘by design’.

New Model Levels (Fast/Thinking/Pro) Continue to Be a Problem for Long Term Projects

Today I noticed there’s now three ‘model’ options available to choose from, Fast, Thinking and Pro. Over the past two weeks I’ve been having major issues related to context retention and the model being too aggressive in pruning info even within 10-20 prompts. When I saw the new model options, I thought maybe that’s solved, but if anything, it’s just verified and codified the shortcomings of 3.0 more. Asking Gemini directly about the differences, it verified that Thinking allows many prompts p…