I think they'll catch up in pure model capabilities but they do such a terrible job of making products from which to use their models that having the best model doesn't end up mattering.
Is Gemini good at writing code? I am sure it is. But where is their Codex? And no, antigravity isn't it.
Is Gemini good at making visualizations? I am sure it is. But where are artifact or visualise skill in gemini.google.com similar to what's available on claude.ai?
What is an average user going to do raw model capability if the product surface isn't expressive enough?
This is weird coz as a user of both Gemini and Claude I have the opposite feeling.
Antigravity CLI is quite decent, it's a huge step up from Gemini CLI (like, for example, it actually fucking works) and has some genuine advantages over Claude Code. Does Codex have something over both of them? I haven't tried it.
But the model just fucking sucks. Before I switched to Claude for personal stuff a few weeks ago, I was like "damn model capabilities are really slowing down" but no, it's just Gemini that's slowing down.
Will have to see if 3.5 Pro is any good when that comes out. But it feels like they would be attempting to catch up to Opus, not to Fable.
FWIW issue is never really about the code it writes it's about general intelligence. Gemini hallucinates like it's 2024, fails to follow instructions, and goes down wildly wrong debugging paths. Opus just gets the job done, first time, every time. With Gemini it feels like "I _am_ glad this intern is working for me but I'm tired of babysitting him" and with Claude it's like "this new PhD guy can replace me soon".
I would be interested to hear what advantages you find Antigravity CLI has over Claude Code.
Nothing major just a few little details:
- the /artifact thing is quite useful (don't think CC has it?)
- the /tasks is a bit better than CC's equivalent
- there are a few built-in skills that I haven't found CC equivalents for in the built in set (but the fact that I haven't sought out 3rd party versions shows you they aren't very important).
And more generally it does a better job of making the agent available. When Claude is debugging something complex and running a bunch of experiments it's often unavailable for like 20 minutes at a time, you only have /btw. Whereas AGY tends to more aggressively use timers and background jobs.
But now I wrote that out, I realised it's probably just as much of a system prompt thing as a harness design thing. Coz Claude _can_ operate that way too.
Anyway, like I said none of these come anywhere near balancing out the model quality gap.