The performance of Gemini 2.5 Pro has significantly decreased!

Google AI Studio
,
1

Pure feelings

Background:

  1. I have been using Gemini 2.5 Pro for article editing and research work, primarily utilizing its ability to generate prompts tailored to the specific themes of each research topic or article, aiding in both research and article polishing.

  2. I have been using Gemini 2.5 Pro for this work for two months, from June to the present.

  3. My workflow is as follows:

I write a paragraph outlining my understanding of the research topic or article, then provide Gemini with a main prompt that includes a segment for generating research prompts and another for article polishing prompts, instructing it to specialize the corresponding System Prompt; subsequently, I use these two System Prompts to drive Gemini 2.5 Pro for research and polishing tasks respectively.

Issues:

  1. Recently, Gemini 2.5 Pro has been prone to forgetting content, performing poorly with lengthy prompts, and struggling to understand the preceding content beyond 30k characters. (This is even with Media resolution set to Medium.)

  2. Editing quality has deteriorated significantly. My instructions for the large model were to “preserve the original text as much as possible while ensuring logical coherence in the article.” However, the results showed that large sections of arguments and points were deleted from the article.

  3. The large model’s thinking and response times have significantly decreased. This may be related to the model’s poor performance.

I can understand Google’s generosity in the face of increasing pressure from its growing global user base, and the measures it has taken in response to this pressure, such as halving its quota.

However, I really miss the excellent text processing capabilities of Gemini 2.5 Pro, the best large model.

In fact, as a user with multiple accounts and a loyal Google member, I don’t mind Google charging a reasonable fee for its services.

3

Hi @Cdkk_Wmfg,

Thank you for your feedback. We appreciate you taking the time to share your thoughts. To help us investigate the issue effectively, any additional details you can provide would be very helpful.

Could you share a complete, self-contained prompt that previously yielded a high-quality result but now produces a poor one? Ideally, please provide both the old response (if saved) and the new response.

Regarding the “forgetting context” issue, could you provide an example of a prompt and pinpoint the specific part of the context the model appears to be ignoring? What was the approximate character or token count of that prompt?

Lastly, for the slower response times, could you give us an estimate of the change?