The available evidence does not establish that Claude Code, Codex, and Google Antigravity were all used to build the same note-taking app, or that one proved to be “in a different league.” The honest answer is that there is no verified winner for that exact test. The tools offer distinct workflows, and other reported comparisons reach task-specific conclusions rather than a universal ranking.
Was there a verified three-way note-taking app test?
No. The available account from Tom’s Guide compares Claude Code and Codex on a subscription tracker, a grocery-price comparison tool, and a financing calculator—not a note-taking app, and not Google Antigravity. A separate May 2026 report summarizes XDA journalist Parth Shah’s month-long comparison of all three across different work, including debugging inherited scripts and creating a personal website. It does not establish the note-taking-app build described in this headline.
As an Amazon Associate I earn from qualifying purchases.
That means the phrase “different league” cannot be treated as a measured result for this app. Without a shared prompt, disclosed versions and model settings, equivalent starting conditions, and a record of human intervention and repairs, a first-person verdict would remain one tester’s experience—not proof that one agent is generally superior.
Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallWhat the other comparisons actually found
In Amanda Caswell’s Tom’s Guide comparison, Claude Code was the author’s pick for the subscription tracker, while Codex won the grocery-price and financing-calculator tasks. The article names Codex its overall winner but qualifies that verdict by user preference and the desired depth of work. Those results apply to that author’s prompts and setup, not to a note-taking app or every coding task.
#1 Best Overall
Parth Shah’s month-long trial, as summarized by MeriStation in May 2026, favored Antigravity for combining autonomous agents with an IDE where the user could intervene directly. The report also notes performance and stability concerns during his trial. Because the tasks and setups differ, that preference does not contradict the Tom’s Guide results; the accounts are not a head-to-head benchmark.
How the three tools approach coding work
Claude Code
Anthropic documents Claude Code as a tool for natural-language feature requests and bug fixes across files, git operations and pull requests, and integrations through MCP. Projects can use CLAUDE.md instructions, skills, and hooks; the product also supports parallel agents and work across terminal, IDE, desktop, and web surfaces. Anthropic says some handoffs require a claude.ai subscription. See Anthropic’s Claude Code overview for the current documented workflow and access details.
Codex
OpenAI highlights parallel agents, code review, browser and computer tools for verification, and cloud environments that can continue running tasks. Codex is available through ChatGPT, editors, and terminal. OpenAI’s Codex page listed usage with ChatGPT Plus and showed Plus at $20 per month when accessed on October 4, 2026; that is a dated plan price, not a guarantee of current pricing or limits. Check OpenAI’s Codex page for current availability and plan terms.
Free tools Windows power users keep installed
One-click scans. No signup required.
Google Antigravity IDE
Google describes Antigravity IDE as an agentic development environment. Its agents can work across the editor, terminal, and browser, including asynchronous and parallel tasks; browser actuation can support UI testing. The environment can produce review artifacts such as plans, diffs, diagrams, images, and browser recordings. Google says Antigravity IDE is not supported for enterprise customers and directs enterprise users to Antigravity 2.0 or CLI. Google’s Antigravity IDE documentation explains its features and availability.
Rank #3
What would make a note-taking app comparison fair?
A useful comparison should judge the finished app, not just how quickly an agent produces code or how polished its interface looks in a screenshot. The testers would need to disclose whether each tool received the same prompt, starter files, time allowance, model and version settings, and level of human help. They would also need to test the resulting app against the same requirements.
- Core behavior: Can users create, edit, search, organize, and delete notes reliably?
- Persistence: Do notes survive refreshes, restarts, and the storage conditions the app claims to support?
- Correctness and recovery: Do key actions work, and what happens when input is invalid or a task fails?
- Usability and accessibility: Is the interface clear and usable with keyboard navigation and assistive technologies?
- Verification and oversight: Does the agent test its work, show useful evidence, and let the developer inspect changes?
- Repair effort: How much human debugging, re-prompting, and code cleanup does the result require?
These criteria can reveal meaningful differences in quality and workflow. The available accounts do not document a common test of these factors across all three tools on a note-taking app, so they cannot settle which one builds the best version.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Which one should you choose?
Choose by the workflow you want to work in, then evaluate the result on your own task. Claude Code’s documented features suit developers who want configurable codebase work across terminal and other surfaces. Codex foregrounds cloud tasks, parallel agents, and verification tools. Antigravity IDE brings agents into an editor alongside terminal and browser work, with artifacts for reviewing what they did. These are workflow distinctions, not evidence that one produces better note-taking apps.
Recommended Free Tools
Before committing to a paid setup, check each vendor’s current access requirements and limits. Anthropic notes subscription requirements for some Claude Code handoffs; OpenAI’s listed Codex access and Plus price can change. The cited documentation describes product capabilities, but it does not provide a controlled quality ranking.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
