Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

composio.dev

Post reply on HN
Print view View original

31–40 of 336 posts

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#31

Post by amarcheschi »

redog wrote: post #24
bratao wrote: post #5

From my use case, the Gemini 2.5 is terrible. I have a complex Cython code in a single file (1500 lines) for a Sequence Labeling. Claude and o3 are very good in improving this code and following the commands. The Gemini always try to do unrelated changes. For example, I asked, separately, for small changes such as remove this unused function, or cache the arrays indexes. Every time it completely refactored the code a…

For me I had to upload the library's current documentation to it because it was using outdated references and changing everything that was working in the code to broken and not focusing on the parts I was trying to build upon.

using outdated references and docs is something i've experienced more or less with every model i've tried, from time to time

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#34

Post by rockwotj »

amarcheschi wrote: post #31
redog wrote: post #24

Earlier quoted context omitted.

For me I had to upload the library's current documentation to it because it was using outdated references and changing everything that was working in the code to broken and not focusing on the parts I was trying to build upon.

using outdated references and docs is something i've experienced more or less with every model i've tried, from time to time

I am hoping MCP will fix this. I am building an MCP integration with kapa.ai for my company to help devs here. I guess this doesn’t work if you don’t add in the tool

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#35

Post by bilekas »

iammrpayments wrote: post #33

Theo video detected = opinion rejected Also I generally dislike thinking models for coding and prefer faster models, so if you have something easy gemini 2.0 is good

Theo has some strange takes for my liking but to flat out reject the opinion isn't the way to go. Thinking models are okay for larger codebases though where some more context is important, this ensures the results are a bit more relevant than say for example Copilot which seems to be really quick at generating some well known algorythms etc.

They're just different tools for different jobs really.

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#37

Post by hyperbovine »

bratao wrote: post #5

From my use case, the Gemini 2.5 is terrible. I have a complex Cython code in a single file (1500 lines) for a Sequence Labeling. Claude and o3 are very good in improving this code and following the commands. The Gemini always try to do unrelated changes. For example, I asked, separately, for small changes such as remove this unused function, or cache the arrays indexes. Every time it completely refactored the code a…

Maybe the Unladen Swallow devs ended up on the Gemini team.

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#38

Post by itchyjunk »

ldjkfkdsjnv wrote: post #15
bratao wrote: post #5

From my use case, the Gemini 2.5 is terrible. I have a complex Cython code in a single file (1500 lines) for a Sequence Labeling. Claude and o3 are very good in improving this code and following the commands. The Gemini always try to do unrelated changes. For example, I asked, separately, for small changes such as remove this unused function, or cache the arrays indexes. Every time it completely refactored the code a…

Yup, gemini 2.5 is bad.

Were you also trying to edit the same code base as the GP or did you evaluate it on some other criteria where it also failed?

Re: Gemini 2.5 Pro vs. Claude 3.7 Sonnet: Coding Comparison

#40

Post by FirmwareBurner »

qwertox wrote: post #13

Gemini is the only model which tells me when it's a good time to stop chatting because either it can't find a solution or because it dislikes my solution (when I actively want to neglect security). And the context length is just amazing. When ChatGPT's context is full, it totally forgets what we were chatting about, as if it would start an entirely new chat. Gemini lacks the tooling, there ChatGPT is far ahead, but a…

>Gemini is the only model which tells me when it's a good time to stop chatting because either it can't find a solution or because it dislikes my solution

Claude used to also do that. Only ChatGPT starts falling apart when I start to question it then gives in and starting to give me mistakes as answers just to please me.

Post reply on HN