Gemini CLI at this stage isn't good at complex coding tasks (vs. Claude Code, Codex, Cursor CLI, Qoder CLI, etc.). Mostly because of the simple ReAct loop, compounded by relatively weak tool calling capability of the Gemini 2.5 Pro model.
> I haven't tried complex coding tasks using Gemini 3.0 Pro Preview yet. I reckon it won't be materially different.
Gemini CLI is open source and being actively developed, which is cool (/extensions, /model switching, etc.). I think it has the potential to become a lot better and even close to top players.
The correct way of using Gemini CLI is: ABUSE IT! With 1M Context Window (soon to be 2M) and generous daily (free) quota are huge advantages. It's a pity that people don't use it enough (ABUSE it!). I use it as a TUI / CLI tool to orchestrate tasks and workflows.
> Fun fact: I found Gemini CLI pretty good at judging/critiquing code generated by other tools LoL
Recently I even hook it up with homebrew via MCP (other Linux package managers as well?), and a local LLM powered Knowledge/Context Manager (Nowledge Mem), you can get really creative abusing Gemini CLI, unleash the Gemini power.
I've also seen people use Gemini CLI in SubAgents for MCP Processing (it did work and avoided polluting the main context), can't help laughing when I first read this -> https://x.com/goon_nguyen/status/1987720058504982561
Gemini CLI is a wild beast. The stories of it just going bonkers and refactoring everything it reads on its own are not rare. My own experience was something like, "Edit no code. Only give me suggestions. blah blah blah" first thing it does is edit a file without any other output. It's completely unreliable.
Pro 3 is -very- smart but it's tool use/following directions isn't great.
I've been using Gemini 3 in the CLI for the past few days. Multiple times I've asked it to fix one specific lint error, and it goes off and fixes all of them. A lot of times it fixes them by just disabling lint rules. It makes reviewing much harder. It really has a mind of its own and sometimes starts grinding for 20 minutes doing all kinds of things - most of them pretty good, but again, challenging to review. I wish it would stick to the task.
> I haven't tried complex coding tasks using Gemini 3.0 Pro Preview yet. I reckon it won't be materially different.
In my limited testing, I found that Gemini 3 Pro struggles with even simple coding tasks. Sure, I haven't tested complex scenarios yet and have only done so via Antigravity. But it is very difficult to do that with the limited quota it provides. Impressions here - https://dev.amitgawande.com/2025/antigravity-problem
Are we using different models? Here is a simulation of Chernobyl reactor 4 using research grade numerical modeling I made with it in a few days: https://rbmk-1000-simulator-162899759362.us-west1.run.app/
Thanks for sharing, insightful.
Personally, I consider Antigravity was a positive & ambitious launch. Initial impression was that there are many rough edges to be smoothed out. I hit many errors like 1. communicating with Gemini (Model-as-a-Service) 2. Agent execution terminated due to errors, etc., but somehow it completed the task (verification/review UX is bad).
Pricing for paid plans with AI Pro or Workspace would be key for its adoption, when Gemini 3.x and Antigravity IDE are ready for serious work.
Interesting. I did not face many issues while communicating with Gemini. But I believe these issues will iron themselves out -- Google does feel to have rushed the launch.
The trick with Gemini is to uploading the whole (or the relevant part of the) codebase (depending on the size) as an xml (using repomix et al) then telling it to output whole files.
With a good prompt and soem trial and error in system instructions, as long as you agree to play the agent yourself, it's unmatched.
CLI? Never had any success. Claude Code leaves it in dust.