Google Antigravity
Free coding agent app on Gemini Flash; Claude 5.5 needs AI Pro at $19.99/month. Change the data setting first.
Should you use it?
Pick it if
People who want to try a coding agent app for free on Gemini 3.8 Flash, with several agents running at once.
Best for: Trying a free coding agent app with several agents running at once (Coding agents Top 20)
Skip it if
You need the top coding models without a subscription, or don't want your code reviewed to improve Google's products.
You give up: Free plan runs on weaker Gemini Flash; top Claude models need AI Pro at $19.99
The short version
- What this is
- Google's free desktop app and CLI for running AI coding agents, with Gemini and some Claude models to choose from.
- Why it matters
- It is Google's main coding agent app and free to start, so many newcomers will meet it; the free models and data terms matter.
- Free to use with weekly limits; AI Pro at $19.99/month adds Claude Sonnet 5.5 and Opus 5.5 s3 s4.
- Google may use and review your interactions unless you change the setting s5.
Good at
Our take
Antigravity is free to start and runs several coding agents at once s1 s2. The free plan's models are Gemini 3.8 Flash and older ones, plus Claude Sonnet 4.6 and Opus 4.6, which Google says it will remove on 2 Nov 2026 s3. Gemini 3.8 Flash ranks 31 of 142 on arena.ai WebDev s6. To get Claude Sonnet 5.5 or Opus 5.5 you need a paid Google AI Pro plan at $19.99 a month s3 s4.
Google's terms say it may use your interactions to improve its products and machine learning, and that people at Google may review them; you can change that in settings s5. Do that before working on private code. The pages give no numbers for the rate limits s1 s3.
Not scored yet
This is a First look: the call above comes from the maker's own pages, so there is no score yet. When an independent coding-agent benchmark publishes current results for Antigravity.
CodingAgents
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
Alternatives
Better or cheaper for coding, from our scores, then the ones we'd also look at. The same kind of product comes first.
- OpenCodeTop scoredCoding agent80FreeScores 80 in coding, first in our ranking; free. Side by side
- OpenAI Codex CLICoding agent70$20 a monthOpen-source terminal agent with ChatGPT Plus; close to the top published coding-agent score at about $1 per task. Side by side
- Claude CodeCoding agent70$20 a monthRuns on Opus 5.5, top of arena.ai WebDev, from $20/month. Side by side
- ClineCoding agentFirst look: Worth tryingFreeOpen source, works with any provider's API key or a local model. Side by side
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 6
- s1Google Antigravity pricing
- s2Google Antigravity home page
- s3Google Antigravity docs: Models
- s4Google AI plans (Gemini subscriptions)
- s5Google Antigravity terms
- s6arena.ai Code Arena: WebDev leaderboard
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 2 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- First look. No independent test of Antigravity itself yet, so not rated.
- Swapped the Copilot alternative for Codex CLI, the best-scoring non-Anthropic coding agent on Artificial Analysis.
Use it well 3 guides on this site
Pages on this site that help with the jobs above.