Claude vs Gemini

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to Claude
   Claude✓fullprobed7/10

   A probe confirms Claude's support site serves a working llms.txt (HTTP 200) listing topic links, and numerous individual documentation pages are available in clean .md format (e.g. claude-docs-1 through 63 all resolve as .md URLs), making the docs directly consumable by an agent. Missing for 10: confirmation that llms.txt/agent-readable docs exist on the main claude.com domain (only support.claude.com was probed), and independent/community evidence that agents actually consume these successfully rather than just first-party doc structure.

   • [probe] “PROBE llms.txt: HTTP 200 at https://support.claude.com/llms.txt # Claude Help Center > Search for answers or browse by topic ## English #…”
   • [claimed-docs] “You can prompt Claude to search through your previous conversations to find and reference relevant information in new chats.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.claude.com/en/.md”

   proof ↗⚑ flag

   Gemini—none0/10

   No evidence that Gemini can be pointed at llms.txt or agent-oriented documentation formats; the evidence only covers uploading files, GitHub repos, and connecting to apps, none of which address consuming llms.txt or agent-facing docs conventions. Missing for 10: any mention of llms.txt support, agent-oriented doc parsing, or a documented workflow for feeding agent-discovery docs to Gemini.

   ⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round drawn
   Claude—none0/10

   The evidence describes Claude Code as a terminal tool and mentions CLI/print output structure, but there is no documentation or claim of headless/non-interactive execution, CI pipeline integration, or scriptable automation mode for Claude products.

   • [claimed-docs] “Build with Claude Code in your terminal, then deploy to a URL Claude can reach”
   • [claimed-docs] “The screen reader mode brings Claude Code back to the basic terminal experience: plain, sequential text with added labels and cues”
   • [community] “src/cli/print.ts is the single worst function in the codebase by every metric: 3,167 lines long, 12 levels of nesting at its deepest, ~486 b…”

   proof ↗⚑ flag

   Gemini—none0/10

   The evidence pack is dominated by consumer-facing Gemini Apps documentation (chat, image generation, Gemini Live, notebooks) and contains no first-party documentation of a headless mode, CI integration, or automation-friendly API/CLI usage. The only hint of a CLI tool appears in community complaints (gemini-comm-14, gemini-comm-15) about login failures for Workspace accounts trying to use 'Gemini CLI' for software development, which does not establish that headless/CI automation works.

   • [community] “I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber, but I now learn I should be a 'Gemini Code Assist Standard or Ent…”
   • [community] “'Failed to login. Ensure your Google account is not a Workspace account.' ... now as a Workspace account I cant use Gemini CLI for my work, …”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round to Claude
   Claude✓fullprobed9/10

   Claude documents connecting to both remote MCP servers via custom connectors and installing local MCP servers on Claude Desktop as easily as browser extensions, plus a unified directory for finding/installing connectors, letting Claude use their tools. Missing for 10: independent/hands-on verification of MCP tool usage reliability beyond vendor docs.

   • [claimed-docs] “Build your own remote MCP servers to connect with any tool.”
   • [claimed-docs] “You can: Connect Claude to existing remote MCP servers. Build your own remote MCP servers to connect with any tool.”
   • [claimed-docs] “You can: - Connect Claude to existing remote MCP servers. - Build your own remote MCP servers to connect with any tool.”
   • [claimed-docs] “installing and managing local MCP servers has become significantly easier... install local MCP servers on your computer as easily as browser…”
   • [claimed-docs] “you can now install local MCP servers on your computer as easily as browser extensions”
   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”
   • [probe] “official MCP server documented at https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp”

   proof ↗⚑ flag

   Gemini—none0/10

   Evidence covers Gemini Apps' 'Connected Apps' feature (Gmail, Calendar, Maps, Flights) and coding-related uploads (GitHub repos, folders), but nothing describes plugging in Model Context Protocol (MCP) servers as a tool-connection mechanism. Missing for 10: any documentation or mention of MCP server support, MCP client configuration, or third-party tool registration via MCP standard.

   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
   • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
   • [claimed-docs] “Get started with Connected Apps in Gemini **Important:** For now, Gemini can’t use Connected Apps in Gemini in Google Messages.”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to Gemini
   Claude!disputedcontradicted6/10

   Anthropic ships an official CLI, Claude Code, well documented for terminal-based coding, deployment, debugging, and even screen-reader accessibility (claude-docs-8, claude-docs-23, claude-docs-52, claude-docs-65). However, a hands-on community report describes it as an 'empty unresponsive terminal' upon first use, contradicting the polished experience implied by docs, and another notes serious code-quality issues in the CLI's own codebase (claude-comm-13, claude-comm-15). missing for 10: broader independent corroboration of reliable day-to-day CLI usage, resolution of reported unresponsiveness, and evidence the code-quality issues have been fixed.

   • [claimed-docs] “Build with Claude Code in your terminal, then deploy to a URL Claude can reach. Test and verify in the browser with the Chrome extension. De…”
   • [claimed-docs] “Build with Claude Code in your terminal, then deploy to a URL Claude can reach. Test and verify in the browser with the Chrome extension.”
   • [claimed-docs] “Build with Claude Code in your terminal, then deploy to a URL Claude can reach”
   • [claimed-docs] “It was built with and for screen reader users, and it's useful to anyone who wants plain output for braille displays, slow connections, or t…”
   • [community] “Tried claude code, and have an empty unresponsive terminal. Looks cool in the demo though, but not sure this is going to perform better than…”
   • [community] “src/cli/print.ts is the single worst function in the codebase by every metric: 3,167 lines long, 12 levels of nesting at its deepest, ~486 b…”

   proof ↗⚑ flag

   Gemini~partialcommunity4/10

   Community discussion confirms the existence of an official 'Gemini CLI' used for software development (comm-13, comm-14), but there is no first-party documentation of it in the evidence pack, and a hands-on report shows it fails to work for Workspace accounts ('Failed to login... now as a Workspace account I cant use Gemini CLI for my work') (comm-15). Missing for 10: official CLI documentation/spec, installation and usage guides, and evidence that login/account restrictions have been resolved.

   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and also how it leverages that huge 1M context…”
   • [community] “I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber, but I now learn I should be a 'Gemini Code Assist Standard or Ent…”
   • [community] “'Failed to login. Ensure your Google account is not a Workspace account.' ... now as a Workspace account I cant use Gemini CLI for my work, …”

   proof ↗⚑ flag

5. ai-native userDrive the product through a documented public API

   weight 3 · round to Gemini
   Claude~partialprobed3/10

   Evidence only hints at API-like surfaces (an Enterprise Compliance API for audit/chat data access, and references to using the Claude API/Console to power products) but never surfaces the actual general-purpose public API documentation for driving Claude's core capabilities; automated probes for an OpenAPI/swagger spec on the docs site returned 404s. Missing for 10: direct citation of the main Claude API reference docs, authentication/quickstart guides, and confirmation of comprehensive public API coverage beyond compliance/audit data.

   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access.”
   • [claimed-docs] “Enterprise includes everything in the Team plan, plus the following: - Security features to ensure the safety and compliance of your organiz…”
   • [claimed-docs] “You can use the prompt improver in the Claude Console to automatically adapt prompts that were originally written for other AI models.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

   Gemini~partialcommunity5/10

   Community evidence confirms a public Gemini API exists and is actively used by developers (pricing tiers, model versions, Google AI Studio parameters like temperature and top_k), but the evidence pack contains no first-party API reference documentation, and one community report notes undocumented/hidden parameter behavior (fixed top_k, capped temperature) that limits full programmatic control. missing for 10: first-party API reference/docs citation, SDK/auth documentation, confirmation that documented parameters match actual behavior.

   • [community] “API pricing is up to $2/M for input and $12/M for output. For comparison: Gemini 2.5 Pro was $1.25/M for input and $10/M for output, Gemini …”
   • [community] “I'm sure this is a very impressive model, but gemini-3-pro-preview is failing spectacularly at my fairly basic python benchmark. In fact, ge…”
   • [community] “My favorite benchmark is to analyze a very long audio file recording of a management meeting and produce very good notes along with a transc…”
   • [community] “Temperature continues to be gated to maximum of 0.2, and there's still the hidden top_k of 64 that you can't turn off. I love the google AI …”
   • [community] “It still failed my image identification test (a photoshopped picture of a dog with 5 legs)... Gemini 3 however, while still failing, at leas…”

   proof ↗⚑ flag

6. ai-native userBuild against official SDKs

   weight 2 · round drawn
   Claude—none0/10

   The evidence pack covers Claude's consumer/enterprise features (Cowork, Projects, connectors, MCP, Chrome extension, file handling) but contains no documentation of official language SDKs (e.g., Python/TypeScript client libraries) for building applications against the Claude API. Missing for 10: any first-party SDK docs, API reference, or code samples showing programmatic API usage.

   ⚑ flag

   Gemini—none0/10

   The evidence pack only covers Gemini's consumer-facing app features (uploads, Gemini Live, Gems, connected apps) and does not document any official SDKs for building applications (e.g., Python/Node/Go SDKs for the Gemini API). Community mentions reference API pricing and a 'Gemini CLI' having login issues, but no concrete SDK documentation or hands-on developer usage evidence is present.

   • [community] “API pricing is up to $2/M for input and $12/M for output. For comparison: Gemini 2.5 Pro was $1.25/M for input and $10/M for output, Gemini …”
   • [community] “'Failed to login. Ensure your Google account is not a Workspace account.' ... now as a Workspace account I cant use Gemini CLI for my work, …”

   proof ↗⚑ flag

7. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Claude—none0/10

   No evidence pack item describes webhooks or event subscription mechanisms for Claude; the closest agentic integrations are MCP connectors and scheduled tasks, which are not webhook-based event subscriptions.

   ⚑ flag

   Gemini—none0/10

   No evidence in the pack describes Gemini offering a webhook subscription mechanism for events; the docs cover imports, connected apps, Gems, Live, Deep Research, etc., but nothing about outbound webhooks or event subscriptions for AI-native/agentic integration.

   ⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round drawn
   Claude✓fullclaimed8/10

   Claude can ingest user data (files, connectors to Gmail/Drive/Calendar, Projects knowledge bases) and generate AI-driven insights, analysis, visualizations, and reports directly from that data, including agentic multi-step research that synthesizes findings with citations. This is well documented across file analysis, Research mode, Cowork task automation, and artifact/document generation features. Missing for 10: independent hands-on benchmarking specifically validating insight quality/accuracy from user data (community evidence is mixed/general rather than about this specific data-insight capability).

   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”
   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “With research, Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”
   • [claimed-docs] “produce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”

   proof ↗⚑ flag

   Gemini✓fullcommunity8/10

   Gemini's docs show robust support for generating insights from user data: uploading documents/spreadsheets/photos/videos for 'answers, summaries, and insights' (gemini-docs-25), Notebooks for organizing and querying sources (gemini-docs-11, gemini-docs-24, gemini-docs-29), Deep Research for in-depth analysis (gemini-docs-7), and Connected Apps that summarize Gmail and productivity data (gemini-docs-30). Independent hands-on reports corroborate real usage: navigating large codebases effortlessly (gemini-comm-13), replacing an OCR vendor for document ingestion with strong accuracy (gemini-comm-17), and NotebookLM being 'really powerful for comprehending large corpuses' (gemini-comm-19), though one report notes weaker accuracy on visual bounding-box tasks (gemini-comm-18). missing for 10: broader independent benchmarking specifically on insight-generation quality across data types, and resolution of the noted accuracy gaps in some visual tasks.

   • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”
   • [claimed-docs] “Notebooks provide a continuous chat experience that remembers your sources, instructions, and ongoing discussions.”
   • [claimed-docs] “you can use notebooks to organize your projects in a dedicated, focused space.”
   • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
   • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and also how it leverages that huge 1M context…”
   • [community] “I work in fintech and we replaced an OCR vendor with Gemini at work for ingesting some PDFs... Processing time went from something like 12 m…”
   • [community] “I've been using NotebookLM powered by Gemini 2.0 for three projects and it is really powerful for comprehending large corpuses you can't pos…”
   • [community] “Unfortunately Gemini really seems to struggle on this, and no matter how we tried prompting it, it would generate wildly inaccurate bounding…”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork's scheduled tasks let users describe a task once and have Claude execute it autonomously on a recurring or on-demand basis, delivering finished outputs like reports and briefings without further user input, which directly matches background automation. Missing for 10: independent/hands-on verification of scheduled task reliability and no detail on failure handling or notification mechanisms.

   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “brings Claude Code's agentic capabilities to knowledge work beyond coding”

   proof ↗⚑ flag

   Gemini~partialclaimed6/10

   Google's docs explicitly describe scheduling recurring actions so Gemini becomes part of daily/weekly/monthly routines (gemini-docs-8), and the Daily Brief feature autonomously delivers a personalized digest without user prompting (gemini-docs-32/41), supported by action-taking integrations with other apps (gemini-docs-10/17/23/30). However, evidence is limited to first-party docs with no independent/hands-on confirmation of reliability, no detail on trigger conditions, failure handling, or scope of what 'recurring actions' can actually do autonomously. Missing for 10: independent verification that scheduled automations run reliably unattended, documentation on trigger/condition logic, and evidence of broader autonomous multi-step task execution beyond simple digests.

   • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
   • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round to Claude
   Claude✓fullclaimed9/10

   Claude's built-in Cowork feature explicitly lets users delegate multi-step tasks ('describe an outcome, step away, come back to finished work'), with agentic execution including browser/computer use, scheduling, and research that autonomously plans next steps. This is well-documented first-party functionality directly matching task delegation to a built-in assistant. Missing for 10: independent hands-on verification of Cowork's delegation reliability (community evidence covers Claude Code/coding use more than Cowork specifically).

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “brings Claude Code's agentic capabilities to knowledge work beyond coding”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”

   proof ↗⚑ flag

   Gemini✓fullcommunity8/10

   Gemini's docs show extensive task delegation: connected apps to take actions in Gmail/Calendar/Maps/Flights (gemini-docs-10, gemini-docs-23, gemini-docs-30), scheduled recurring actions (gemini-docs-8), custom Gems for specific goals (gemini-docs-9), Deep Research for autonomous multi-step research (gemini-docs-7), and Daily Brief proactive digests (gemini-docs-32, gemini-docs-41). Community evidence corroborates real-world delegated use cases like large codebase analysis and audio transcription (gemini-comm-13, gemini-comm-10). missing for 10: independent hands-on verification specifically of agentic task delegation/action-taking (vs. just Q&A), and evidence of reliability/success rate when Gemini executes multi-step delegated tasks.

   • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
   • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
   • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and also how it leverages that huge 1M context…”
   • [community] “My favorite benchmark is to analyze a very long audio file recording of a management meeting and produce very good notes along with a transc…”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round to Claude
   Claude✓fullcommunity9/10

   Claude's entire interface is natural-language chat/voice, and documentation shows this extends to agentic actions—generating files, browsing/clicking the web, using the computer, scheduling recurring tasks, and building artifacts—all triggered by describing the desired outcome in plain language (claude-docs-4,6,7,15,37,38,54). Community evidence corroborates real-world agentic use (claude-comm-1,10,12), though some report friction with CLI usability. Missing for 10: independent benchmark of NL command reliability across all surfaces, and no rebuttal to the CLI unresponsiveness anecdote being addressed.

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “build tools, visualizations, and experiences by simply describing what you need”
   • [community] “I've been running Opus 4.8 for agentic coding and I don't see it being significantly better than Sonnet 4.5. I find that pairing Google Gemi…”
   • [community] “Anecdotal, but it 1 shot fixed a UI bug that neither Opus 4.5/Codex 5.2-high could fix.”
   • [community] “Claude is significantly better than other models at code assistant tasks, or at least in the way I use it.”

   proof ↗⚑ flag

   Gemini✓fullclaimed8/10

   Gemini is fundamentally operated via natural-language chat and voice (Gemini Live's free-flowing conversation, 'Hey Google' voice commands, text prompts for image generation, scheduling recurring actions, custom Gems, and connected-app actions) rather than rigid commands or GUIs, per extensive first-party docs. Missing for 10: independent/hands-on verification that complex natural-language action requests (e.g., connected-app task execution) reliably work as described, and community evidence is mixed on model quality/accuracy for specific tasks rather than confirming the NL interface itself.

   • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more de…”
   • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini.”
   • [claimed-docs] “With Gemini Live, you can: * **Talk back and forth:** Talk to Gemini without typing, and Gemini will respond back verbally.”
   • [claimed-docs] “you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more details or change th…”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
   • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
   • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
   • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
   • [claimed-docs] “On Android, say “Hey Google” to ask Gemini for help with what’s on your screen”

   proof ↗⚑ flag

Api quality

1. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Claude—none0/10

   The evidence pack covers Claude's consumer features, connectors, Cowork, and MCP integrations, but contains no mention of API versioning schemes or a documented deprecation policy for any Claude/Anthropic API. Since Claude does expose developer-facing APIs (e.g., for Console, Claude Code, MCP), this axis is applicable, but no evidence supports it.

   ⚑ flag

   Gemini—none0/10

   The evidence pack is entirely consumer-focused Gemini Apps documentation (image generation, Gemini Live, connected apps, notebooks) and general community sentiment about model quality/pricing; there is no mention of API versioning, version lifecycle, or a documented deprecation policy anywhere in the pack.

   ⚑ flag

Agent mode

1. power-userDelegate a multi-step task that the assistant works on autonomously in the background and returns for my review

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork is documented as letting users describe a multi-step outcome, step away, and return to finished work, with scheduled/recurring tasks and background agentic execution (browser/computer use, file generation) explicitly designed for delegation and later review. Missing for 10: independent hands-on validation of Cowork's reliability/quality for complex delegated tasks and clearer detail on review/approval workflow beyond docs.

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “This article explains how to use Claude Cowork, which brings Claude Code's agentic capabilities to knowledge work beyond coding.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”

   proof ↗⚑ flag

   Gemini~partialclaimed6/10

   Deep Research lets users delegate an open-ended research task that Gemini works on autonomously and returns a report for review, and scheduled/recurring actions show background task automation; Connected Apps/Gems add some autonomous action-taking on the user's behalf. However there's no clear evidence of a general-purpose multi-step 'agent mode' that plans and executes across arbitrary apps end-to-end with an explicit review/approval step, nor independent hands-on confirmation of this workflow. Missing for 10: evidence of a broad autonomous agent (beyond Deep Research/scheduling) handling arbitrary multi-step tasks across apps, and independent/community validation of such background task delegation working reliably.

   • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
   • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
   • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”

   proof ↗⚑ flag

2. power-userHave the assistant operate a web browser on my behalf to research and complete tasks on websites

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude has multiple documented browser-control capabilities: the built-in browser in Cowork that opens sites, reads pages, clicks, types, and fills forms autonomously (claude-docs-6/67), the Claude in Chrome extension that reads/clicks/navigates websites (claude-docs-63), and computer-use navigation for on-screen actions (claude-docs-7/22/59), enabling research and task completion on websites. Missing for 10: independent hands-on validation of browser-task success rates and reliability under real-world site complexity.

   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to swit”
   • [claimed-docs] “Claude in Chrome is a browser extension that allows Claude to read, click, and navigate websites alongside you.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “When computer use is enabled and Claude doesn't have a connector or tool for what you need, it may navigate to your screen directly—clicking…”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”

   proof ↗⚑ flag

   Gemini~partialclaimed4/10

   Deep Research lets Gemini conduct 'in-depth and real-time research' across web sources, and Connected Apps let it take actions in other apps (Gmail, Calendar, Maps, Flights) with permission — showing some research/task-automation capability. However, there is no evidence of Gemini actually driving a web browser (navigating pages, clicking, filling forms) to complete tasks on arbitrary websites, only sanctioned first-party app integrations. Missing for 10: explicit browser-control/agentic navigation evidence, hands-on demonstration of completing a multi-step website task, independent corroboration of this capability.

   • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
   • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”

   proof ↗⚑ flag

3. power-userLet the assistant see and operate applications on my computer to complete work

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork/computer use lets Claude navigate directly to the user's screen—clicking, typing, opening apps, filling forms—while the user watches, plus a built-in browser for opening sites and interacting with pages, directly matching the story of operating applications to complete work. Community evidence corroborates agentic coding/task use though notes mixed quality perceptions unrelated to this specific capability. Missing for 10: independent hands-on verification of computer-use reliability/accuracy and broader third-party benchmarking beyond vendor docs.

   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “When computer use is enabled and Claude doesn't have a connector or tool for what you need, it may navigate to your screen directly—clicking…”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to swit”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Claude in Chrome is a browser extension that allows Claude to read, click, and navigate websites alongside you.”

   proof ↗⚑ flag

   Gemini~partialclaimed5/10

   Gemini's Connected Apps feature lets it take actions in other apps (Gmail, Calendar, Maps, Flights) with permission, and on Android it can see what's on-screen to help with context, but this is limited to a curated set of app integrations/APIs rather than general computer-use/desktop automation across arbitrary applications. Missing for 10: broader OS-level screen perception, ability to click/type across arbitrary desktop apps, and independent hands-on evidence of an agentic computer-use mode.

   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
   • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
   • [claimed-docs] “On Android, say “Hey Google” to ask Gemini for help with what’s on your screen”
   • [claimed-docs] “Get started with Connected Apps in Gemini **Important:** For now, Gemini can’t use Connected Apps in Gemini in Google Messages.”

   proof ↗⚑ flag

Tasks

1. power-userSchedule recurring or one-off tasks that run automatically and come back to me with results

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork explicitly supports scheduled tasks that run on a recurring or one-off basis and deliver finished outputs like reports and summaries back to the user, matching the story closely. Missing for 10: independent/hands-on validation of scheduling reliability and no detail on notification/delivery mechanisms beyond docs.

   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”

   proof ↗⚑ flag

   Gemini~partialclaimed6/10

   Gemini docs confirm scheduling recurring actions (gemini-docs-8) and Daily Brief personalized digest (gemini-docs-32/41), showing one-off/recurring automated tasks that return results. However, evidence lacks detail on task complexity, multi-step agent tasks, notification delivery mechanisms, or independent/community corroboration of this specific feature working reliably. missing for 10: detailed documentation on scheduling flexibility, agentic multi-step task execution, notification/result delivery mechanisms, and independent hands-on validation of the scheduled-tasks feature.

   • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”

   proof ↗⚑ flag

Apps

1. power-userUse an official desktop app with OS-level shortcuts and access to what is on my screen

   weight 2 · round drawn
   Claude~partialclaimed5/10

   Claude ships an official desktop app (Mac, Windows, Linux via apt) and a Cowork/computer-use feature that lets Claude 'navigate to your screen directly—clicking, typing, and opening apps' while the user watches, which shows real screen access. However there is no evidence of dedicated OS-level keyboard shortcuts (e.g., a global hotkey to invoke Claude with current screen context) — the screen access described is agentic task automation rather than a power-user shortcut workflow. Missing for 10: documented OS-level global shortcuts/hotkeys, and evidence that a user can quickly summon Claude to see the current screen via keypress rather than launching a Cowork/computer-use task.

   • [claimed-docs] “you can install Claude Desktop from Anthropic's apt repository rather than as a downloaded .deb file so that updates arrive through your sys…”
   • [claimed-docs] “The Claude desktop apps bring Claude's capabilities directly to your computer, allowing for seamless integration with your workflow.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “When computer use is enabled and Claude doesn't have a connector or tool for what you need, it may navigate to your screen directly—clicking…”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would”
   • [claimed-docs] “This article explains how to use Claude Cowork, which brings Claude Code's agentic capabilities to knowledge work beyond coding.”

   proof ↗⚑ flag

   Gemini~partialclaimed5/10

   Docs confirm an official Mac desktop app with a global OS-level keyboard shortcut (Option+Space) to summon Gemini without opening a browser [gemini-docs-15, gemini-docs-36, gemini-docs-20], but the only 'see what's on your screen' capability documented is for the Android mobile app via 'Hey Google' [gemini-docs-6], not the desktop app. Missing for 10: evidence of desktop screen-reading/screenshare capability, and independent/hands-on confirmation of the desktop shortcut and screen access working together.

   • [claimed-docs] “you can also use the keyboard shortcut Option + Space to bring up the Gemini chat window after the app is installed and running”
   • [claimed-docs] “The Gemini app provides quick access to AI features, allowing you to get help with writing, brainstorming, coding, and more, without needing…”
   • [claimed-docs] “What you need to use the Gemini app on Mac * A personal Google Account you manage on your own, or a work or school account that your adminis…”
   • [claimed-docs] “On Android, say “Hey Google” to ask Gemini for help with what’s on your screen”

   proof ↗⚑ flag

2. knowledge-workerUse full-featured official mobile apps for iOS and Android

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Official iOS and Android apps are documented (App Store install instructions, Chrome/mobile chat parity across web/iOS/Android/desktop, voice mode explicitly available on Claude Mobile), indicating full-featured mobile apps rather than a bare wrapper. Missing for 10: no independent hands-on review of mobile app feature parity/quality, and no detail on which advanced features (Cowork, computer use) are available on mobile vs desktop-only.

   • [claimed-docs] “You can install the Claude app onto your iOS device by navigating to the App Store and searching for “Claude by Anthropic””
   • [claimed-docs] “You can install the Claude app onto your iOS device by navigating to the App Store and searching for "Claude by Anthropic"”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop ... Memory across conversations”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop”
   • [claimed-docs] “Voice mode is a beta feature available to all plans (Free, Pro, Max, Team, and Enterprise) on Claude Mobile (iOS and Android), Claude Deskto…”

   proof ↗⚑ flag

   Gemini~partialclaimed6/10

   Docs confirm a full-featured Gemini mobile app with rich functionality (Gemini Live voice conversations, screen-aware Android assistant via 'Hey Google', Maps/Flights integration, daily briefs, scheduling, image generation, coding help) showing strong Android support, and generic mobile-app language implies broader availability, but the evidence never explicitly names or details an iOS app or iOS-specific parity. missing for 10: explicit iOS app documentation/feature parity, App Store presence, and any cross-platform comparison confirming equal functionality on iOS vs Android.

   • [claimed-docs] “On Android, say “Hey Google” to ask Gemini for help with what’s on your screen”
   • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more de…”
   • [claimed-docs] “Make plans with Google Maps and Google Flights”
   • [claimed-docs] “The Gemini app provides quick access to AI features, allowing you to get help with writing, brainstorming, coding, and more, without needing…”
   • [claimed-docs] “get help with writing, brainstorming, coding, and more, without needing to open a web browser.”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
   • [claimed-docs] “If you have access to Gemini Apps with a work or school account, some Gemini mobile app features aren’t available.”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”

   proof ↗⚑ flag

Custom bots

1. power-userBuild and share custom assistants with their own instructions and knowledge

   weight 2 · round drawn
   Claude~partialclaimed6/10

   Claude supports Projects (self-contained workspaces with custom knowledge bases/files) and Skills (teach Claude repeatable instructions like brand guidelines), which together let a power-user build a persona-like assistant with instructions and knowledge; Projects can be shared with team members. However, there's no dedicated 'custom GPT'-style public sharing/marketplace for assistants, and no independent evidence of end-to-end sharing outside an org. missing for 10: evidence of public/marketplace sharing of custom assistants, explicit persona/system-instruction configuration UI, and independent hands-on confirmation of building and sharing such assistants.

   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “whether that's creating documents with your company's brand guidelines, analyzing data using your organization's specific workflows”
   • [claimed-docs] “Skills teach Claude how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelin…”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”

   proof ↗⚑ flag

   Gemini~partialclaimed6/10

   Gemini's "Gems" feature (gemini-docs-9) lets power-users create a custom Gem with its own instructions and requirements, and Gems can be given knowledge via uploaded files/sources (gemini-docs-25), directly matching the core of this story. However, evidence does not confirm a straightforward sharing/publishing mechanism for Gems to other users, nor independent hands-on validation of the feature's robustness. Missing for 10: documentation of sharing/publishing custom Gems with other users, evidence of knowledge-base scope/limits, and independent community corroboration of Gems in practice.

   • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
   • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Gemini
   Claude—none0/10

   The evidence pack documents agentic task automation (Cowork, scheduled tasks, Research) and single-document file handling, but no feature is described for processing or acting on many items at once (e.g., batch file processing, bulk edit across records, or a batch API). Automation-depth stories like this are plausible for Claude given its agentic tooling, but nothing in the pack shows bulk/multi-item operation support.

   ⚑ flag

   Gemini~partialcommunity3/10

   Gemini supports uploading whole code folders/repos and large codebases (a form of bulk ingestion) and can take actions across connected apps or run scheduled recurring actions, but there is no explicit documentation of a bulk/batch operation feature (e.g., applying an action to many items at once like bulk-editing files, mass-tagging, or batch task execution) as an AI-native automation capability. missing for 10: explicit bulk-action/batch-processing feature, evidence of applying one instruction across many discrete items simultaneously, independent corroboration of this specific capability.

   • [claimed-docs] “To add a code folder: click More Uploads Import Code Upload folder.”
   • [claimed-docs] “To add a code folder: click More Uploads ... Import Code ... Upload folder.”
   • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and also how it leverages that huge 1M context…”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round drawn
   Claude~partialclaimed4/10

   Claude Cowork supports scheduled/recurring tasks that run automatically on a time-based schedule or on demand (claude-docs-38, claude-docs-58), which is a form of automation, but there's no evidence of user-defined rules triggered by external events (e.g., 'when an email arrives' or 'when a file changes, do X') as opposed to calendar/time-based scheduling. missing for 10: event-driven trigger conditions (webhooks, connector-based event listeners), a rules engine for conditional automation, and any documentation of non-time-based triggers.

   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”

   proof ↗⚑ flag

   Gemini~partialclaimed4/10

   Gemini supports 'scheduling recurring actions' as part of daily/weekly/monthly routines (gemini-docs-8), which is a form of automation, but this is time-based scheduling rather than user-defined conditional rules that trigger on arbitrary events. Connected Apps let Gemini take actions in other apps (gemini-docs-10, gemini-docs-23, gemini-docs-30) but only in response to a direct user request, not an automatic event trigger. Missing for 10: evidence of event-based (not just time-based) trigger conditions, ability to define custom 'if X happens then do Y' rules, and any confirmation of conditional logic beyond fixed recurring schedules.

   • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork explicitly supports scheduled recurring tasks, letting users describe a workflow once and have Claude execute it automatically on a recurring or on-demand basis, delivering outputs like reports and briefings — this directly matches the story. Missing for 10: independent/hands-on verification of scheduling reliability and details on scheduling granularity/limits beyond vendor docs.

   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”

   proof ↗⚑ flag

   Gemini~partialclaimed6/10

   Gemini docs explicitly confirm scheduling recurring actions ('daily, weekly, and monthly routines') via a dedicated feature (gemini-docs-8), and Daily Brief shows an example of a recurring automated digest (gemini-docs-32/41). However, evidence lacks detail on workflow complexity, chaining multiple steps/tools, error handling, or independent/community validation of this scheduling feature. missing for 10: detail on multi-step workflow scheduling, chaining across apps, reliability/error handling, and independent hands-on confirmation.

   • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”

   proof ↗⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round drawn
   Claude—none0/10

   No evidence describes versioning, reviewing, or rolling back automations like scheduled Cowork tasks or Skills; docs cover creating/scheduling tasks but not history, diffs, or rollback capability.

   ⚑ flag

   Gemini—none0/10

   No evidence of version control, review workflows, or rollback capabilities for automations (e.g., scheduled actions, Gems, or connected app actions). The evidence only covers scheduling recurring actions and connecting apps, with no mention of versioning, diffing, review approval, or rollback of automations.

   ⚑ flag

Connectors

1. power-userBrowse a directory of third-party apps and connectors and add them to the assistant

   weight 2 · round to Claude
   Claude✓fullclaimed9/10

   Claude documents a unified directory that brings skills, connectors, and plugins together in one place to find and install everything that customizes Claude, plus specific connectors like Google Workspace and remote/local MCP servers to extend the assistant. Missing for 10: no independent hands-on review confirming the browsing/discovery UX of the directory itself.

   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”
   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “installing and managing local MCP servers has become significantly easier... install local MCP servers on your computer as easily as browser…”
   • [claimed-docs] “you can now install local MCP servers on your computer as easily as browser extensions”
   • [claimed-docs] “You can: Connect Claude to existing remote MCP servers. Build your own remote MCP servers to connect with any tool.”

   proof ↗⚑ flag

   Gemini~partialclaimed6/10

   Gemini docs describe a 'Connected Apps' feature that lets users link Gmail, Calendar, Maps, Flights and 'a variety of productivity apps' so Gemini can search/create content and take actions, which matches the connectors-directory concept ([gemini-docs-10],[gemini-docs-17],[gemini-docs-23],[gemini-docs-30],[gemini-docs-33],[gemini-docs-19]). However, the evidence never shows a browsable app-store-like directory UI, doesn't clarify how many third-party (non-Google) apps are included, and there's no independent/hands-on confirmation of the browse-and-add experience. Missing for 10: explicit directory/marketplace UI screenshots or docs, breadth of third-party (non-Google) app listings, independent user corroboration of adding connectors.

   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
   • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
   • [claimed-docs] “Get started with Connected Apps in Gemini **Important:** For now, Gemini can’t use Connected Apps in Gemini in Google Messages.”
   • [claimed-docs] “Make plans with Google Maps and Google Flights”

   proof ↗⚑ flag

2. knowledge-workerConnect my cloud drive, email, and calendar so the assistant can search and use them in answers

   weight 3 · round to Claude
   Claude✓fullclaimed9/10

   Claude has a documented Google Workspace connector letting users connect Gmail, Google Calendar, and Google Drive so Claude can search emails, manage calendar, and work with documents/files directly in conversation, plus a privacy commitment not to train on this data. This directly satisfies the story's cloud drive/email/calendar connection use case. Missing for 10: no independent hands-on report corroborating real-world reliability of these specific connectors.

   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “We do not train our models on your Gmail, Drive, or Calendar connector data, ensuring your private information remains private.”
   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”

   proof ↗⚑ flag

   Gemini✓fullclaimed8/10

   Google's docs describe first-party 'Connected Apps' letting Gemini summarize Gmail, create Calendar events, search across productivity apps, and use personal Gmail/Drive as sources for Deep Research, directly matching the story's cloud drive/email/calendar connector requirement. Missing for 10: independent/hands-on verification of search quality and confirmation that calendar reading (not just event creation) works reliably.

   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
   • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
   • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”
   • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
   • [claimed-docs] “Get started with Connected Apps in Gemini **Important:** For now, Gemini can’t use Connected Apps in Gemini in Google Messages.”

   proof ↗⚑ flag

Analysis

1. power-userHave the assistant write and run code on my data to produce charts, computed answers, and downloadable files

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Docs explicitly describe generating downloadable Excel/PowerPoint/Word/PDF files, producing reports with charts and visualizations, and using artifacts to build code-driven visualizations and interactive components from uploaded data files (CSV, XLSX, etc.). This directly matches the power-user story of writing/running code on data to produce charts, computed answers, and downloadable outputs. missing for 10: independent/hands-on community corroboration specifically validating the data-analysis/code-execution-to-chart workflow (community evidence in the pack focuses on coding agent quality, not this analysis feature).

   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “produce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills”
   • [claimed-docs] “Generate code and visualize data”
   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”
   • [claimed-docs] “Claude can work with the following document types: PDF DOCX CSV TXT HTML ODT RTF EPUB JSON XLSX”
   • [claimed-docs] “Common examples of artifact content include: Documents (Markdown or plain text) - Code snippets ... Interactive React components”
   • [claimed-docs] “Common examples of artifact content include: - Documents (Markdown or plain text) - Code snippets - Single-page HTML websites - SVG images -…”
   • [claimed-docs] “Artifacts allow you to turn ideas into shareable apps, tools, or content—build tools, visualizations, and experiences by simply describing w…”
   • [claimed-docs] “build tools, visualizations, and experiences by simply describing what you need”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”

   proof ↗⚑ flag

   Gemini—none0/10

   The evidence pack shows Gemini can import/upload code folders and GitHub repos and get 'insights' from uploaded documents/spreadsheets, but there is no evidence of an actual code-execution/sandbox feature that writes and runs code to produce charts, computed answers, or downloadable output files. No docs or community reports describe this specific data-analysis-with-code-execution workflow.

   • [claimed-docs] “To add a GitHub repository: More Uploads Import Code and enter the GitHub repository or branch URL.”
   • [claimed-docs] “To add a code folder: click More Uploads Import Code Upload folder.”
   • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”

   proof ↗⚑ flag

Artifacts

1. knowledge-workerHave the assistant create and iteratively edit documents, presentations, and other files I can export

   weight 2 · round to Claude
   Claude✓fullclaimed9/10

   Docs explicitly describe generating and editing Excel, PowerPoint, Word, and PDF files via natural-language prompts, plus Artifacts for documents/code/interactive content that can be iteratively refined and downloaded, and uploading/persisting files in Projects for ongoing editing. Missing for 10: independent hands-on review confirming export fidelity/iteration quality across file types.

   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “produce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills”
   • [claimed-docs] “Common examples of artifact content include: Documents (Markdown or plain text) - Code snippets ... Interactive React components”
   • [claimed-docs] “Common examples of artifact content include: - Documents (Markdown or plain text) - Code snippets - Single-page HTML websites - SVG images -…”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”
   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”

   proof ↗⚑ flag

   Gemini~partialclaimed4/10

   Evidence documents Gemini's ability to generate and iteratively edit images (Nano Banana) with export/download at set resolutions, and general writing assistance, but there is no evidence of a dedicated document or presentation creation/editing workflow (e.g., a canvas-style doc/slide editor) with export to file formats. Missing for 10: explicit documentation of creating/iterating on text documents or slide decks, and exporting them to standard file formats (docx/pptx/pdf).

   • [claimed-docs] “You can create captivating images in seconds with Nano Banana 2. From work, play, or anything in between, Gemini Apps can help you generate …”
   • [claimed-docs] “Local edits: Making quick and specific changes to parts of an image.”
   • [claimed-docs] “Character consistency: Maintain the look of a person or character across various generated images, including the ability to combine multiple…”
   • [claimed-docs] “Download images at at 2K resolution with a Google AI plan or at 1K without an AI plan.”
   • [claimed-docs] “Blend text, images, and video to bring your ideas to life.”
   • [claimed-docs] “The Gemini app provides quick access to AI features, allowing you to get help with writing, brainstorming, coding, and more, without needing…”

   proof ↗⚑ flag

Files

1. knowledge-workerUpload documents, spreadsheets, and PDFs and get accurate analysis of their contents

   weight 3 · round to Claude
   Claude✓fullclaimed9/10

   Docs confirm Claude supports uploading PDFs, DOCX, CSV, XLSX, TXT, HTML, ODT, RTF, EPUB, JSON, with analysis of both text and visual elements in PDFs up to 100 pages, plus persistent Project file storage for cross-conversation reference and generation of derived documents/reports. Missing for 10: independent hands-on benchmarking of analysis accuracy across large/complex spreadsheets or long PDFs beyond the 100-page limit.

   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”
   • [claimed-docs] “Claude can work with the following document types: PDF DOCX CSV TXT HTML ODT RTF EPUB JSON XLSX”
   • [claimed-docs] “Claude analyzes both text and visual elements (like images, charts, and graphics) in PDFs of 100 pages or fewer”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”
   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “produce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills”

   proof ↗⚑ flag

   Gemini✓fullcommunity8/10

   First-party docs explicitly state users can upload documents, spreadsheets, and more to get answers, summaries, and insights (gemini-docs-25), and independent hands-on evidence corroborates accurate document/PDF analysis (a fintech user reporting 96% OCR accuracy on PDFs, comm-17) plus praise for NotebookLM's ability to comprehend large source corpora (comm-19). Missing for 10: dedicated evidence on spreadsheet-specific accuracy and broader independent benchmarking across document types beyond the single fintech PDF case.

   • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”
   • [community] “I work in fintech and we replaced an OCR vendor with Gemini at work for ingesting some PDFs... Processing time went from something like 12 m…”
   • [community] “I've been using NotebookLM powered by Gemini 2.0 for three projects and it is really powerful for comprehending large corpuses you can't pos…”

   proof ↗⚑ flag

Memory

1. power-userHave the assistant remember relevant context from previous chats and apply it in new conversations

   weight 3 · round drawn
   Claude✓fullclaimed8/10

   Claude has explicit first-party memory/chat-search docs: it can search previous conversations and "remember context from your chats and carry it into new conversations and Cowork tasks," plus a dedicated article on how memory works, what's remembered, and how to review/edit it; the product page also advertises "Memory across conversations" as a core feature. This directly matches the story of remembering context across chats and applying it in new ones. Missing for 10: independent/hands-on corroboration of memory quality or limitations in practice beyond vendor docs.

   • [claimed-docs] “You can prompt Claude to search through your previous conversations to find and reference relevant information in new chats.”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop ... Memory across conversations”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Claude can also remember context from your chats and carry it into new conversations and Cowork tasks.”

   proof ↗⚑ flag

   Gemini✓fullclaimed8/10

   Gemini docs explicitly describe a personalization feature where 'the memory of your past Gemini chats' informs new conversations, plus user controls to review/delete that activity, confirming both the capability and its persistence across sessions. Missing for 10: independent hands-on validation of cross-chat memory recall accuracy and more detail on scope/duration of retained context.

   • [claimed-docs] “You can get a personalized experience in Gemini Apps based on: The memory of your past Gemini chats”
   • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”

   proof ↗⚑ flag

2. power-userSet persistent custom instructions and preferences that shape every response

   weight 1 · round to Claude
   Claude~partialclaimed6/10

   Claude supports persistent memory/context (chat search and memory, Projects with knowledge bases, custom instructions implied via Skills and Projects) that carries into new conversations, but there is no explicit documented feature for setting global 'custom instructions' that shape every response the way ChatGPT's system prompt does. missing for 10: dedicated persistent custom-instructions/preferences UI applying to all chats, independent/hands-on verification that memory reliably shapes every response, and clarity on scope/limits of what's remembered.

   • [claimed-docs] “You can prompt Claude to search through your previous conversations to find and reference relevant information in new chats.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Claude can also remember context from your chats and carry it into new conversations and Cowork tasks.”
   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “Skills teach Claude how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelin…”

   proof ↗⚑ flag

   Gemini~partialclaimed5/10

   Gemini offers a 'memory of past chats' personalization feature (gemini-docs-18) and custom Gems that let users pre-set instructions/goals (gemini-docs-9), which together approximate persistent customization, but there's no documented single 'custom instructions' setting that explicitly shapes every response across all chats. Missing for 10: explicit persistent instruction/preference settings applied globally to every response, independent verification of memory consistency, and detail on how memory interacts with different chat sessions.

   • [claimed-docs] “You can get a personalized experience in Gemini Apps based on: The memory of your past Gemini chats”
   • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”

   proof ↗⚑ flag

Projects

1. knowledge-workerOrganize related chats and files into a project or space that shares context and instructions

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Projects docs confirm self-contained workspaces with shared chat histories and knowledge bases, persistent file uploads scoped to a project for cross-conversation reference, and memory/chat search to build on prior context. missing for 10: no evidence of custom instructions/system prompt configuration per project beyond files, and no independent/hands-on corroboration of the project workflow in practice.

   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop ... Memory across conversations”

   proof ↗⚑ flag

   Gemini✓fullcommunity7/10

   Gemini's 'Notebooks' feature explicitly provides a continuous, focused space that remembers sources, instructions, and ongoing chat history, and lets users upload documents, code, and other files into that same organized context (gemini-docs-11, gemini-docs-24, gemini-docs-25, gemini-docs-29). Custom Gems (gemini-docs-9) further let users set persistent instructions for recurring tasks, and independent commentary confirms NotebookLM/Notebooks are genuinely useful for organizing large source sets into a coherent project workspace (gemini-comm-19), though that same source flags UI/display shortcomings. Missing for 10: no first-party doc detailing multi-chat organization within one persistent 'project' the way competitors define it, and no hands-on evidence of shared-instruction consistency across many chats in the same notebook.

   • [claimed-docs] “Notebooks provide a continuous chat experience that remembers your sources, instructions, and ongoing discussions.”
   • [claimed-docs] “you can use notebooks to organize your projects in a dedicated, focused space.”
   • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”
   • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”
   • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
   • [community] “I've been using NotebookLM powered by Gemini 2.0 for three projects and it is really powerful for comprehending large corpuses you can't pos…”

   proof ↗⚑ flag

Images

1. knowledge-workerGenerate and edit images from natural-language prompts

   weight 2 · round to Gemini
   Claude~partialclaimed4/10

   Claude can understand and analyze uploaded/pasted images (JPEG, PNG, GIF, WebP) and can produce SVG images, diagrams, and flowcharts as artifacts from natural-language descriptions, but there is no evidence of true raster image generation or photo-editing capability comparable to dedicated image models. Editing of generated visual artifacts is possible via iterative prompting, but this is limited to code-rendered graphics rather than general image generation/editing. Missing for 10: dedicated raster image-generation model, photo editing/inpainting features, and any independent confirmation of image-generation quality.

   • [claimed-docs] “Common examples of artifact content include: - Documents (Markdown or plain text) - Code snippets - Single-page HTML websites - SVG images -…”
   • [claimed-docs] “Claude analyzes both text and visual elements (like images, charts, and graphics) in PDFs of 100 pages or fewer”
   • [claimed-docs] “Claude supports the following image formats: - JPEG - PNG - GIF - WebP”
   • [claimed-docs] “You can also copy images and paste them from your clipboard into Claude”
   • [claimed-docs] “build tools, visualizations, and experiences by simply describing what you need”

   proof ↗⚑ flag

   Gemini✓fullclaimed8/10

   Gemini docs explicitly describe generating and editing images via natural-language prompts (Nano Banana 2), including local edits, character consistency, blending images, and resolution export options. missing for 10: independent hands-on corroboration of image editing quality and no community evidence testing this specific feature.

   • [claimed-docs] “You can create captivating images in seconds with Nano Banana 2. From work, play, or anything in between, Gemini Apps can help you generate …”
   • [claimed-docs] “Local edits: Making quick and specific changes to parts of an image.”
   • [claimed-docs] “Character consistency: Maintain the look of a person or character across various generated images, including the ability to combine multiple…”
   • [claimed-docs] “You can create captivating images in seconds with Nano Banana 2.”
   • [claimed-docs] “Download images at at 2K resolution with a Google AI plan or at 1K without an AI plan.”
   • [claimed-docs] “Blend text, images, and video to bring your ideas to life.”

   proof ↗⚑ flag

2. knowledge-workerShare screenshots and photos and have the assistant accurately interpret what is in them

   weight 2 · round to Claude
   Claude✓fullclaimed7/10

   Claude's docs confirm native image upload/paste support (JPEG, PNG, GIF, WebP) and clipboard paste, plus PDF analysis that includes visual elements like images and charts, directly supporting screenshot/photo interpretation for knowledge workers. Missing for 10: independent/hands-on evidence validating accuracy of image interpretation, and no explicit mention of screenshot-specific use cases (e.g., UI screenshots, photos of documents) beyond general image/PDF support.

   • [claimed-docs] “Claude analyzes both text and visual elements (like images, charts, and graphics) in PDFs of 100 pages or fewer”
   • [claimed-docs] “Claude supports the following image formats: - JPEG - PNG - GIF - WebP”
   • [claimed-docs] “You can also copy images and paste them from your clipboard into Claude”
   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”

   proof ↗⚑ flag

   Gemini!disputedcontradicted4/10

   Docs confirm users can upload photos/screenshots and get insights (gemini-docs-25) and get screen-context help via 'Hey Google' (gemini-docs-6), but hands-on reports show real accuracy failures: Gemini generated 'wildly inaccurate bounding boxes' on images (gemini-comm-18) and failed to correctly interpret a manipulated photo, missing key details even in the latest version (gemini-comm-12). A positive OCR use case exists (gemini-comm-17) but that's for PDFs, not general screenshot/photo scene interpretation, so the core 'accurately interpret' claim is contradicted by concrete hands-on failures. Missing for 10: independent benchmarks specifically on screenshot/UI interpretation accuracy, and resolution of the documented bounding-box/detail-recognition failures.

   • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”
   • [claimed-docs] “On Android, say “Hey Google” to ask Gemini for help with what’s on your screen”
   • [community] “Unfortunately Gemini really seems to struggle on this, and no matter how we tried prompting it, it would generate wildly inaccurate bounding…”
   • [community] “It still failed my image identification test (a photoshopped picture of a dog with 5 legs)... Gemini 3 however, while still failing, at leas…”
   • [community] “I work in fintech and we replaced an OCR vendor with Gemini at work for ingesting some PDFs... Processing time went from something like 12 m…”

   proof ↗⚑ flag

Voice

1. knowledge-workerHave a natural, real-time voice conversation with the assistant

   weight 2 · round drawn
   Claude✓fullclaimed8/10

   Claude ships an explicit Voice mode enabling complete spoken conversations, available across web, desktop, iOS and Android, positioned to work best on phone. Missing for 10: independent hands-on reviews of voice latency/naturalness and confirmation it's out of beta.

   • [claimed-docs] “Voice mode allows you to have complete spoken conversations with Claude.”
   • [claimed-docs] “Voice mode is a beta feature available to all plans (Free, Pro, Max, Team, and Enterprise) on Claude Mobile (iOS and Android), Claude Deskto…”

   proof ↗⚑ flag

   Gemini✓fullclaimed8/10

   Gemini Live is explicitly documented to support natural, free-flowing, interruptible voice conversations where Gemini talks back verbally in real time, directly matching the story. Missing for 10: independent/hands-on community corroboration specifically validating the voice conversation experience (community evidence covers other Gemini features/models but not Live voice interactions).

   • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more de…”
   • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini.”
   • [claimed-docs] “With Gemini Live, you can: * **Talk back and forth:** Talk to Gemini without typing, and Gemini will respond back verbally.”
   • [claimed-docs] “you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more details or change th…”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round drawn
   Claude—none0/10

   The evidence pack details many UI-exclusive Claude.ai features (Cowork, voice mode, computer use, memory/chat search, artifacts, browser extension, scheduled tasks) but contains no documentation that these capabilities are exposed through the Claude API, nor any statement of API/UI feature parity. Enterprise API mentions are limited to a Compliance API for logs, not general feature parity.

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Voice mode allows you to have complete spoken conversations with Claude.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”

   proof ↗⚑ flag

   Gemini—none0/10

   The evidence pack details many Gemini Apps UI-only features (Gems, Deep Research, Connected Apps, Daily Brief, Live conversations, Notebooks, scheduling) with no corresponding API documentation showing these are exposed programmatically. Community evidence (e.g., gemini-comm-11) even notes the API/AI Studio path is more restricted (capped temperature, hidden top_k) than the full product, reinforcing that API and UI capability sets are not equivalent.

   • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
   • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
   • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
   • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more de…”
   • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
   • [community] “Temperature continues to be gated to maximum of 0.2, and there's still the hidden top_k of 64 that you can't turn off. I love the google AI …”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round to Claude
   Claude~partialclaimed6/10

   Claude documents a data-export feature covering conversation and account data, letting users take their data with them ([claude-docs-12], [claude-docs-40]). However, there is no evidence specifying the export format is an open/standard one (e.g., JSON/portable), nor documentation of easy migration/interoperability with other tools, so the 'open format' and full portability aspects of the story are unconfirmed. missing for 10: explicit statement of open/standard export format, evidence of full interoperability/reuse elsewhere, and independent confirmation of export completeness.

   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”

   proof ↗⚑ flag

   Gemini—none0/10

   Evidence covers activity deletion/review (gemini-docs-31) but no mention of exporting data in open/portable formats or data-export tooling for leaving the platform. Missing for 10: any documentation of a data export/download feature (e.g., Google Takeout integration), open-format export options, or independent confirmation of data portability.

   • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Claude—none0/10

   No evidence in the pack mentions data residency, regional storage options, or geographic controls for where account/chat data is stored; the closest items concern export, audit logs, and training opt-outs, none of which address residency choice.

   ⚑ flag

   Gemini—none0/10

   The evidence pack covers Gemini's features and privacy/data-use settings (e.g., activity retention, human review opt-outs) but contains no mention of data residency or regional storage controls for AI-native/enterprise users. missing for 10: any documentation of region selection, data residency guarantees, or enterprise data-location controls.

   ⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude documents explicit user controls to prevent training use: incognito chats are never used to improve Claude even with Model Improvement enabled, users can toggle the 'Model Improvement' privacy setting, and connector data (Gmail/Drive/Calendar) is explicitly excluded from training. This directly satisfies the ai-native privacy-posture story of preventing data from being used for model training. Missing for 10: independent/third-party verification of these claims and explicit default policy for Enterprise/Team plans beyond connectors.

   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “We do not train our models on your Gmail, Drive, or Calendar connector data, ensuring your private information remains private.”

   proof ↗⚑ flag

   Gemini~partialclaimed7/10

   Google's support docs state that chats and uploaded files in Gemini Apps are not reviewed by humans or used to improve generative AI models, and users can manage/delete their activity via 'My Activity' and toggle 'Keep Activity' off (gemini-docs-38, gemini-docs-31). However, a separate doc notes that audio/video from Gemini Live can be used to train models unless the user opts out, showing the training-data control is feature-specific rather than a single unified setting (gemini-docs-37). Missing for 10: a clear, centralized opt-out control covering all Gemini surfaces (not just chat text), independent/hands-on verification that opted-out data is truly excluded from training, and clarity for enterprise/Workspace accounts.

   • [claimed-docs] “Your chats and uploaded files in Gemini Apps won’t be reviewed by human reviewers or otherwise used to improve generative AI models.”
   • [claimed-docs] “You can let Google use your audio and Gemini Live videos and screenshares to improve and develop its services, including training generative…”
   • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Claude✓fullclaimed8/10

   Claude provides explicit user-facing data controls: exporting chat history/user data (claude-docs-12, 40), reviewing/editing/turning off memory (claude-docs-45), incognito chats excluded from training (claude-docs-46), and enterprise audit logs plus a compliance API for data governance (claude-docs-11, 44). Missing for 10: explicit self-service account/data deletion flow documentation and independent verification that deletion requests are honored.

   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Enterprise includes everything in the Team plan, plus the following: - Security features to ensure the safety and compliance of your organiz…”

   proof ↗⚑ flag

   Gemini✓fullclaimed8/10

   Google's support docs explicitly describe controls to review prompts, delete Gemini Apps activity, and turn off 'Keep Activity' (gemini-docs-31), plus explicit statements that chats/files are not used for model training by default (gemini-docs-38) while audio/video in Gemini Live can be opted in/out of training use (gemini-docs-37) — directly matching retention/deletion control for an AI-native user. Missing for 10: independent/hands-on verification that deletion actually removes data, and detail on data export or full account-level deletion workflows.

   • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”
   • [claimed-docs] “You can let Google use your audio and Gemini Live videos and screenshares to improve and develop its services, including training generative…”
   • [claimed-docs] “Your chats and uploaded files in Gemini Apps won’t be reviewed by human reviewers or otherwise used to improve generative AI models.”

   proof ↗⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   Claude~partialclaimed6/10

   Claude documents a 'Model Improvement' privacy setting that can be toggled off and 'incognito chats' that are excluded from training even if Model Improvement is enabled, giving users control over whether their conversations are used to improve the model (claude-docs-46, claude-docs-47). This addresses opt-out of usage-for-training, and data export/deletion options exist (claude-docs-12, claude-docs-40), but there is no explicit documentation of a broader telemetry/analytics opt-out (e.g., product usage metrics, crash reporting) beyond model-training data use. missing for 10: explicit telemetry/analytics tracking opt-out settings, independent confirmation that toggling actually stops all usage tracking, documentation of what non-training telemetry data is collected.

   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”

   proof ↗⚑ flag

   Gemini~partialclaimed6/10

   Docs show Gemini provides some privacy controls: reviewing/deleting prompts and turning off 'Keep Activity' (gemini-docs-31), and settings around whether audio/video/chats are used to improve models (gemini-docs-37, gemini-docs-38). This addresses usage-history and training-data opt-out but not a full 'telemetry/usage tracking' opt-out (e.g., diagnostic/product analytics separate from chat history) and there's no independent verification of these controls' effectiveness. Missing for 10: explicit documentation of a general telemetry/analytics opt-out toggle beyond activity/training-data settings, and independent/hands-on confirmation that opting out actually stops tracking.

   • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”
   • [claimed-docs] “You can let Google use your audio and Gemini Live videos and screenshares to improve and develop its services, including training generative…”
   • [claimed-docs] “Your chats and uploaded files in Gemini Apps won’t be reviewed by human reviewers or otherwise used to improve generative AI models.”

   proof ↗⚑ flag

Research

1. knowledge-workerLaunch a deep research run that autonomously searches many sources and returns a cited report

   weight 3 · round to Claude
   Claude✓fullcommunity8/10

   Claude's Research feature is well documented: it operates agentically running multiple searches that build on each other, determines what to investigate next, and delivers thorough answers in minutes with easy-to-check citations. Community evidence is mixed on research depth (some say it lags ChatGPT/Gemini), which caps quality but the core capability is clearly delivered. Missing for 10: independent hands-on benchmark showing citation accuracy/report quality, and clearer detail on breadth of sources searched.

   • [claimed-docs] “With research, Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”
   • [claimed-docs] “Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [community] “Meanwhile, Claude's general use cases are... fine. For generic research topics, I find that ChatGPT and Gemini run circles around it: in the…”
   • [community] “Works pretty nicely for research still, not seeing a substantial qualitative improvement over Opus 4.5.”

   proof ↗⚑ flag

   Gemini✓fullclaimed7/10

   Gemini Apps has a documented Deep Research feature that conducts in-depth, real-time research across sources and allows adding personal sources (Gmail, Drive, uploads, NotebookLM notebooks) for the research, matching the autonomous multi-source research story. missing for 10: explicit documentation of citation formatting in the final report and independent hands-on evidence of report quality/citation accuracy from third parties.

   • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
   • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”

   proof ↗⚑ flag

2. knowledge-workerGet answers grounded in current web results with citations back to the sources

   weight 2 · round to Claude
   Claude~partialcommunity7/10

   Claude's Research feature is documented to perform agentic multi-step web searches and deliver answers with 'easy-to-check citations' (claude-docs-20, 27, 39, 68), directly matching the story. However, independent community feedback suggests mixed real-world quality—commenters say Claude's general research 'is fine' but that ChatGPT and Gemini 'run circles around it' in depth and presentation (claude-comm-8, claude-comm-9), tempering confidence in how well-grounded/comprehensive the citations truly are. missing for 10: independent hands-on verification of citation accuracy/source quality, and confirmation research draws from live/current web data versus stale index.

   • [claimed-docs] “With research, Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”
   • [claimed-docs] “Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [community] “Meanwhile, Claude's general use cases are... fine. For generic research topics, I find that ChatGPT and Gemini run circles around it: in the…”
   • [community] “Works pretty nicely for research still, not seeing a substantial qualitative improvement over Opus 4.5.”

   proof ↗⚑ flag

   Gemini~partialclaimed6/10

   Gemini's Deep Research feature explicitly supports 'in-depth and real-time research on almost any subject,' implying grounded, current-web-based answers, and users can add further sources for research context. However, the evidence pack never explicitly documents inline citation links back to specific web sources, nor independent confirmation that citations are reliably shown. Missing for 10: explicit documentation of citation/source-linking UI, independent verification that citations are accurate and consistently displayed.

   • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
   • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”

   proof ↗⚑ flag

Admin

1. team-adminManage members, permissions, and data policies for my organization's workspace

   weight 2 · round to Claude
   Claude~partialclaimed4/10

   Evidence confirms Enterprise plan admin/security features like audit logs and a Compliance API for programmatic access to usage data, implying some org-level governance, but there is no documentation of member management, role/permission assignment, or granular data policy controls for team admins. missing for 10: member invitation/removal workflows, role-based permission management, workspace-level data retention/policy settings, and independent corroboration of admin console functionality.

   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access.”
   • [claimed-docs] “Enterprise includes everything in the Team plan, plus the following: - Security features to ensure the safety and compliance of your organiz…”

   proof ↗⚑ flag

   Gemini—none0/10

   Evidence only shows end-user features (image generation, Live conversations, notebooks, connected apps) and passing mentions that a 'work or school account' administrator can 'enable Gemini,' but there is no evidence of an admin console for managing members, setting permissions, or configuring org-wide data policies.

   ⚑ flag

Data controls

1. knowledge-workerExport my complete chat history and account data

   weight 1 · round to Claude
   Claude✓fullclaimed9/10

   Claude's docs explicitly state individual users can export user information and chat history from Settings > Privacy, and that exports include both conversation data and account/user data; Enterprise adds a Compliance API for programmatic access to chat histories and file content. Missing for 10: independent/hands-on confirmation of export completeness or format details beyond first-party docs.

   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”

   proof ↗⚑ flag

   Gemini—none0/10

   The evidence only covers reviewing and deleting Gemini activity via My Activity (gemini-docs-31) and privacy settings for Live audio (gemini-docs-37, gemini-docs-38), but there is no mention of exporting chat history or account data (e.g., via Google Takeout or a dedicated export tool). missing for 10: any documentation of an export/download feature for chat history or account data, independent confirmation of export completeness.

   • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”

   proof ↗⚑ flag

2. knowledge-workerControl whether my conversations are used to train models

   weight 3 · round drawn
   Claude✓fullclaimed8/10

   Claude provides explicit privacy controls: incognito chats are excluded from model training even with Model Improvement enabled, a 'Model Improvement' opt-in/out toggle exists, and connector data (Gmail/Drive/Calendar) is explicitly excluded from training. Missing for 10: independent/hands-on verification that the training opt-out is actually honored in practice, and clearer documentation of the toggle's exact location/scope for all plan tiers.

   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “We do not train our models on your Gmail, Drive, or Calendar connector data, ensuring your private information remains private.”

   proof ↗⚑ flag

   Gemini✓fullclaimed8/10

   Google's own support docs state that by default chats/uploaded files aren't used to improve generative AI models unless a user opts in via 'Keep Activity', and that users can review, delete activity, or turn off Keep Activity at any time; separately, users must explicitly consent to let Google use Gemini Live audio/video for model training. This gives knowledge-workers clear, documented control over whether conversations feed model training. Missing for 10: independent/hands-on verification that these settings work as described and clarity on enterprise/Workspace account defaults.

   • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”
   • [claimed-docs] “You can let Google use your audio and Gemini Live videos and screenshares to improve and develop its services, including training generative…”
   • [claimed-docs] “Your chats and uploaded files in Gemini Apps won’t be reviewed by human reviewers or otherwise used to improve generative AI models.”

   proof ↗⚑ flag