compare to chat gpt 4o, not even close. i think it even worse than 4o mini. other AI like claude 3.5 sonnet, o1-mini,preview did pretty good at coding, why dont gemini?

Bc Gemini’s main feature is a big context window (2 million tokens for Pro). And Google entered the LLM race much later than Openai and Anthropic. Openai were the first in this field in general, no wonder they are still the leaders and they have sota model o1. Though honestly I think o1 is just finetune on long thought data, no change in architecture, just training costs but not development costs. I assume google is also now either thinking or already working on a similar finetune.

By the way, if you need to perform some task related to the code, then you can clearly instruct the model, system instructions are needed for this. In the Gemini web version (not in ai studio), some kind of system prompt is also written first. And if you need the behavior of the model close to o1, then I made a prompt that makes the model think the same way o1 does. Someone wrote that the results have really improved, heh.

Why gemini 1.5 pro bad at coding?

Google AI Studio

klinok64 October 25, 2024, 9:52pm 5

Here is the prompt

Topic		Replies	Views
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 Google AI Studio gemini-15 , ai-studio , api , models , gemini-20	3	402	January 21, 2025
Gemini wrote the wrong code! Google AI Studio gemini	1	259	February 2, 2025
Gemini Pro 3.1 -what kind of coding in AI Studio Google AI Studio gemini-3	2	589	March 3, 2026
Critically poor performance of the latest gemini-2.5 model Google AI Studio models	5	1696	July 6, 2025
Gemini 3 review after 1 month: inconsistent at best, poor at worst compared to Gemini 2.5 Google AI Studio gemini-3	9	4405	February 16, 2026

Why gemini 1.5 pro bad at coding?

Related topics