Be advised: this thread is not for serious in-depth discussion of weighty topics (we have a link for that), this thread is not for anything Culture War related. This thread is for Fun. You got jokes? Share 'em. You got silly questions? Ask 'em.
- 221
- 1
Jump in the discussion.
No email address required.
Notes -
I'm actually a huge fan or 3.1 pro (high) personally. Opus and 5.x xhigh are definitely better at difficult problem solving but 3.1 pro can handle most things and is much more chill and less anal about many things.
Would be interesting to hear what specific tasks 3.1 pro underperforms on that opus can take care of
I've tried to use Gemini 3.1 pro to handle some basic coding tasks at work, and it does not do particularly well. I don't want to give exact specifics to avoid doxxing myself, but I can give you the shape of it. Skip to the most direct example if you don't feel like reading.
I have a java project. Currently it uses all-java libraries for image processing. Java kind of sucks for image processing because the integrated entry point always loads the entire raster into memory at once. If you have a limited heap, you're going to run into a world of pain trying to work with the standard library.
To get around that problem, I've looked at a native library that has java FFM bindings. Unfortunately, to use FFM, I had to upgrade to JDK 25. We had some test failures, and I figured that Gemini/antigravity could handle that kind of scutwork. It could not. It tried to make massive, architecture-level changes to two different subsystems in our codebase rather than just fix a classloader problem. Eventually I gave up and did it myself. I lost about a day to this.
After upgrading the JDK, I handed off the work to another developer to handle writing a small wrapper around the FFM library to unpack the native libs. She immediately tried to use Gemini, and lost four days to its confabulations. She came back to me repeatedly telling me it was impossible, and that we couldn't possibly do this on windows because Gemini gave her a trivially disprovable assertion. I eventually gave up and handed it to another developer who engaged his brain and had it done in a few hours, on all our supported platforms, with tests.
The most direct example: After that, I started converting one of our image processing routines to use the native lib. I figure that since the problem was easy and both the native library and the FFM bridge are both exquisitely documented, and they're both open source, this should be trivial for Gemini. Well, it turns out that both the native lib and the FFM bridge were both mostly written after January 2025, so neither 3.1 Pro and 3.6 flash consistently had the APIs inside their training window. It also didn't really have many examples to match on because this isn't a basic Python CRUD app.
You would not believe the absolute fever dream of a codebase it tried to cook up. It couldn't get function names right, and when it could, it couldn't consistently distinguish between the native library and the bridge. It frequently failed to even be consistently wrong. Eventually it finished, and it solved the problem by importing the FFM bridge but not actually using any of the underlying native calls.
I was a little disappointed.
RIP in pepeloni. But to be fair most agentic ai loves to do this unless you prompt it correctly.
More options
Context Copy link
More options
Context Copy link
To be honest, I don't know if I can compare them fairly. My access to 3.1 pro was clearly a budget option or something, because I would constantly be shunted back down to "Thinking" because of pro being in high demand.
I also didn't have a Claude Code-like option, but attempting to feed 3.1 pro my code worked for a single response, and then it claimed to be unable to remember it for the next question. Possibly, I could have kept giving the entire 5k lines of code for every question, but that seemed ridiculous.
In contrast, I pointed Claude Code at my project directory, typed "/init" and it very accurately determined what the purpose of the project was and all the specifics from just the code, test output, and poor documentation.
With that said, for smaller code questions 3.1 pro was certainly adequate.
Ohhh you got access to the gemini.com app not access to the api wrapper. Yeah the app sucks, idk how google screwed it up so much.
Also the gemini bundled with the $25 google workspace accounts is especially gimped, it's much worse than thr $20 plan that normal users get.
3.1 pro high is good in antigravity, aistudio, and api.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link