Gemini 2.5 Pro is a better coding model, but Gemini CLI is way behind Claude Code, perhaps because the model itself isn’t well-tuned for agentic work. If you’re just doing targeted refactoring and exploration, you can copy and paste back and forth from the web app for $20 a month.

Gemini 2.5 Pro made some big post-launch improvements for tool calling/agentic usage that made it go from “pulling teeth” to “almost as smooth as Claude” in Cline/Roo Code (which is saying something since Cline was originally built around Claude tool use specifically).

So the team at least seems to be aware of its shortcomings in that area and working to improve it with some success which I appreciate.

But you are correct that Gemini CLI still lags behind for whatever reason. It gets stuck in endless thought loops way too often for me, like maybe 1/15 tasks hits a thought loop burning API credits or it just never exits from the “Completing task, Verifying completion, Reviewing completion, Assessing completion status…” phase (watching the comical number of ways it rephrases it is pretty funny though).

Meanwhile I’ve only had maybe one loop over a period of a couple months using Gemini 2.5 Pro heavily in Roo Code with the most recent version so it seems like an issue with the CLI specifically.

Even just a week ago Gemini was still outputting the same message twice almost every time in Cline, I doubt that has changed in the last week.

Hmmm I haven't used for Cline for several months but in Roo I have made some (fairly minor) changes to my Roo Code code modes and have not experienced this at all. Especially that frequently, I use GPT 4.1 via my Copilot Pro plan and Gemini 2.5 Pro via OpenRouter as my daily drivers. That being said I have had found using Gemini through the AI Studio API much less reliable in Roo/Cline and I'm not sure how you are accessing it.

I have auto approve turned on for most routine tasks and run Gemini for relatively long (by Cline/Roo standards) tasks unsupervised without issue, with the normal caveats of any LLM going off the deep end every now and then but haven't seen that more frequently with Gemini except in the first couple months 2.5 Pro was released.

I mostly use RooCode nowadays, which works well enough with both Claude and Gemini and other models, even locally hosted ones. Decoupling the LLM vendor from the tools might miss out on some finer features, but also gives me a little bit more freedom, much like how you can also do with the Copilot plugins and Continue.dev and a few others.

Note: all of them sometimes screw up applying diffs, but in general are good enough.

Not if you write Rust. From regularly producing code that has unbalanced braces or quote characters somewhere to destroying well working code. It also easily gets into loops where it can't solve a problem, comes up with a half-working solution A, throws it away, comes up with B, then C, then goes back to A etc.

I run Gemini Pro from within CC but I only use it for analysis and planning for which it is better than Claude (Opus).

I guess if your target language is Python or JS/TS etc., your milage may be considerably better.

For Rust it's simply not true.

Are you saying Claude is better at writing Rust or Gemini? Or Gemini in Gemini CLI? Not following. In my experience, Gemini 2.5 PRO is better at writing Rust overall.

My experience is Claude is better at writing rust than Gemini. Gemini cli gets confused easily. But has good higher level picture. In my use case where Gemini is the architect, it even provides full code changes to claude (does not directly compile most of the time, misses move of structs) and claude makes those changes. It works better for me that way.

This is my strategy as well. I definitely have surges of usage.

Except for one catastrophic binge where I accidentally left Opus on for a whole binge (KILL ME!!!), I use around $150/month. I like having the spigot off when I am not working.

Would the $100/month plan plus API for overflow come out ahead? Certainly on some months. Over the year, I don't know. I'll let you know.

Can anyone help compare a cost comparison between Gemini 2.5 pro vs Claude Code on a plan or API?