>"It doesn't matter, the real benchmark is taking the community temperature on the model after a few weeks of usage."
Indeed. It's almost impossible to truly know a model before spending a few million tokens on a real world task. It will take a step-change level advancement at this point for me to trust anything but Claude right now.
To this day, I still don't understand why Claude gets more acclaim for coding. Gemini 2.5 consistently outperformed Claude and ChatGPT mostly because of the much larger context.
I'm not sure about this. I used gemini and claude for about 12 hours a day for a month and a half straight in an unhealthy programmer bender and claude was FAR superior. It was not really that close. Going to be interesting to test gemini 3 though.
Gemini 2.5 is prone to apology loops, and often confuses its own thinking to user input, replying to itself. Chat GPT 5 likes to refuse tasks with "sorry I can't help with that". At least in VSCode's GitHub Copilot Agent mode. Claude hasn't screwed up like that for me.
Different styles of usage? I see Gemini praised for being able to feed the whole project and ask changes. Which is cool and all but... I never do that. Claude for me is better for specific modifications to specific parts of the app. There's a lot of context behind what's "better".
I can't really explain why I have barely used Gemini.
I think it was just timing with the way models came out. This will be the first time I will have a Gemini subscription and nothing else. This will be the first time I really see what it can do fully.
Gemini 2.5 and now 3 seem to continue their trend of being horrific in agentic tasks, but almost always impress me with the single first shot request.
Claude Sonnet is way better about following up and making continuous improvements during a long running session.
For some reason Gemini will hard freeze-up on the most random queries, and when it is able to successfully continue past the first call, it only keeps a weird summarized version of its previous run available to itself, even though it's in the payload. It's a weird model.
My take is that, it's world-class at one-shotting, and if a task benefits from that, absolutely use it.
I use Gemini cli, Claude Code and Codex daily. If I present the same bug to all 3, Gemini often is the one missing a part of the solution or drawing the wrong conclusion. I am curious for G3.
Claude doesn’t gaslight me, or flat out refuses to do something I ask it to because it believes it won’t work anyway. Gemini does
Gemini also randomly just reverts everything because of some small mistake it found, makes assumptions without checking if those are true (eg this lib absolutely HAS TO HAVE a login() method. If we get a compile error it’s my env setup fault)
