Claude vs Grok
Claude wins · 31–10 (9 drawn)
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
Agent access
ai-native userPoint an agent at llms.txt or agent-oriented docs
weight 2 · round to GrokA 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”
The docs site serves a discoverable llms.txt (HTTP 200, describing itself as official xAI developer documentation) and every doc page is also available in plain markdown form, which is exactly the agent-oriented docs pattern the story asks for. Missing for 10: independent/community confirmation that agents actually consume this llms.txt successfully in practice.
- [probe] “PROBE llms.txt: HTTP 200 at https://docs.x.ai/llms.txt # SpaceXAI API Documentation > Official SpaceXAI (xAI) developer documentation at ht…”
- [claimed-docs] “Grok 4.6, SpaceXAI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API. It has a 500k context wi…”
- [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
ai-native userRun the product headlessly / in CI for automation
weight 2 · round to GrokClaudenone0/10The 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…”
The xAI API (REST, OpenAPI spec confirmed via probe, streaming, structured outputs, quickstart script) provides a clear headless programmatic interface suitable for automation/CI, and community mentions a 'terminal' mode for Grok Build. However there is no explicit CI/CD documentation, GitHub Actions example, or non-interactive automation guide. missing for 10: dedicated CI/CD integration docs, GitHub Actions or pipeline examples, explicit 'headless mode' documentation.
- [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
- [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
- [claimed-docs] “Streaming outputs is **supported by all models with text output capability**”
- [claimed-docs] “Structured Outputs lets the API return responses in a specific format, for example, a JSON object matching a schema you define”
- [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”
- [community] “still waiting for a proper gui for grok build - terminal is nice but codex desktop app is very useful”
ai-native userPlug MCP servers into this product so it can use their tools
weight 3 · round to ClaudeClaude 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”
xAI docs explicitly describe adding custom MCP connectors and tunneling a local MCP server so Grok can reach it and use its tools, alongside built-in OAuth connectors for other tools (grok-docs-2, grok-docs-3, grok-docs-38, grok-docs-19). Missing for 10: independent/hands-on confirmation that custom MCP tool-calling works reliably in practice, and more detail on protocol/version compatibility.
- [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
- [claimed-docs] “A tunneling service solves this by exposing your local server through a public URL that Grok can connect to.”
- [claimed-docs] “When you add a custom MCP connector, Grok's servers need to reach your MCP server over the public internet.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
ai-native userUse an official CLI
weight 2 · round drawnClaudedisputedcontradicted6/10Anthropic 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…”
There's no official CLI documentation for Grok, but a community comment references a terminal-based interface for 'Grok Build' ('terminal is nice but codex desktop app is very useful'), suggesting some CLI-like coding tool exists even though it isn't documented in the official docs pack. missing for 10: official CLI documentation/reference, installation instructions, and command examples confirming a first-party CLI product.
- [community] “still waiting for a proper gui for grok build - terminal is nice but codex desktop app is very useful”
- [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
ai-native userDrive the product through a documented public API
weight 3 · round to GrokEvidence 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…”
xAI publishes a full public REST API with documented endpoints for text, image, video, tool use, structured outputs, and an OpenAPI spec confirmed live by probe, plus a quickstart guide, satisfying the AI-native/agentic driving story. missing for 10: independent third-party benchmarking of API reliability/completeness beyond xAI's own docs and anecdotal community chatter about tool-calling quirks.
- [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
- [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
- [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
- [claimed-docs] “Structured Outputs lets the API return responses in a specific format, for example, a JSON object matching a schema you define”
- [claimed-docs] “Streaming outputs is **supported by all models with text output capability**”
- [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”
- [probe] “PROBE llms.txt: HTTP 200 at https://docs.x.ai/llms.txt # SpaceXAI API Documentation > Official SpaceXAI (xAI) developer documentation at ht…”
ai-native userIssue scoped/least-privilege API credentials for an agent
weight 2 · round drawnClaudenone0/10No evidence describes scoped or least-privilege API credential issuance for agents; enterprise features mention audit logs and compliance API access but nothing about creating scoped/restricted API keys or credentials for agent use. Missing for 10: any documentation of API key scoping, permission tiers, or least-privilege credential management for agents.
Groknone0/10The xAI API is a developer product with API keys, so scoped/least-privilege credential issuance is a fair capability to expect, but the evidence pack contains no mention of API key scopes, roles, granular permissions, or least-privilege credential controls — only OAuth-based connector authentication (grok-docs-19) for built-in tools, which is about connecting Grok to external services, not issuing scoped agent credentials.
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
ai-native userBuild against official SDKs
weight 2 · round to GrokClaudenone0/10The 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.
The evidence shows an official xAI developer API with a published OpenAPI spec, quickstart docs, and text-generation/tool-use guides (grok-docs-20, grok-docs-27, grok-probe-3), which implies programmatic access an AI-native builder could use, but none of the evidence explicitly names or documents an official SDK (e.g., Python/JS client library) as opposed to raw REST/OpenAPI usage. Missing for 10: explicit documentation of a first-party SDK package, install instructions, or code samples showing SDK usage, plus any independent/community confirmation of SDK quality or adoption.
- [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
- [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
- [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”
- [probe] “PROBE llms.txt: HTTP 200 at https://docs.x.ai/llms.txt # SpaceXAI API Documentation > Official SpaceXAI (xAI) developer documentation at ht…”
ai-native userSubscribe to events via webhooks
weight 2 · round drawnClaudenone0/10No 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.
Groknone0/10No evidence of any webhook subscription mechanism for Grok events; the docs describe connectors, tools, image/video generation, and inbound MCP tunneling, but nothing about outbound event notifications or webhook endpoints. Missing for 10: any webhook subscription API, event types, or delivery/registration mechanism.
Agentic features
ai-native userGet AI-generated insights and suggestions from my data inside the product
weight 2 · round to ClaudeClaude 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.”
Grok's connectors (Gmail/Calendar, Google Drive, Microsoft Teams, Salesforce, custom APIs/MCP) let it read and act on a user's own data inside the chat, and features like Realtime Multi-agent Research suggest Grok can analyze and synthesize that data into insights. However, the evidence is mostly first-party docs describing data access rather than concrete examples of proactive 'insights and suggestions,' and one hands-on report notes Grok has 'real trouble with agentic tool calling,' undercutting confidence in reliable in-context analysis. Missing for 10: independent hands-on demonstration of Grok surfacing unprompted insights/suggestions from connected data, and confirmation that tool-calling reliability issues don't undermine this in practice.
- [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [claimed-docs] “Search emails using Gmail search operators (`from:`, `to:`, `subject:`, `newer_than:`, `has:attachment`, etc.).”
- [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”
- [claimed-docs] “Search across channels and chats, read messages, send new messages, reply to threads, and create chats — all without leaving Grok.”
- [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
- [community] “I experimented with Grok 4 for openclaw... It was more verbally fluid than 5.5, but had real trouble with agentic tool calling - the model f…”
ai-native userSet up automations that run autonomously in the background
weight 2 · round to ClaudeClaude 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”
Grok Bot is described as an AI teammate running on a 'persistent cloud computer' and Grok supports multi-agent orchestration for research tasks, hinting at some background/autonomous agent capability, but there is no documentation of scheduling, triggers, or recurring/timed automation setup. Missing for 10: explicit scheduling/trigger mechanism, details on how automations run without user prompting, and independent confirmation of autonomous background execution.
- [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
- [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
ai-native userDelegate tasks to a built-in AI assistant inside the product
weight 3 · round to ClaudeClaude'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.”
Grokdisputedcontradicted6/10xAI docs describe strong built-in agentic delegation — Grok Bot hands work to 'AI teammates on a persistent cloud computer,' Realtime Multi-agent Research orchestrates multiple agents for research tasks, and connectors let Grok act on email/calendar/Salesforce from chat (grok-docs-15, grok-docs-26, grok-docs-11, grok-docs-16, grok-docs-19). However, hands-on community testing directly contradicts smooth agentic delegation: a user reports Grok 'had real trouble with agentic tool calling - the model felt like it hadn't been trained to think of tool calling as one of its primary modalities' (grok-comm-6), and another notes the lack of a proper GUI for Grok Build limiting usability (grok-comm-7). Missing for 10: independent verification that Grok Bot/multi-agent research reliably completes delegated tasks end-to-end, and resolution of the reported tool-calling weakness.
- [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
- [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
- [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
- [claimed-docs] “Create new records - Add Leads, Opportunities, Accounts, Cases, or records on custom objects directly from chat.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [community] “I experimented with Grok 4 for openclaw... It was more verbally fluid than 5.5, but had real trouble with agentic tool calling - the model f…”
- [community] “still waiting for a proper gui for grok build - terminal is nice but codex desktop app is very useful”
ai-native userOperate the product with natural-language commands
weight 2 · round to ClaudeClaude'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.”
Grok's docs describe a chat/voice interface where natural-language input drives text generation, image/video creation, and connector actions like creating Salesforce records or searching email 'directly from chat' (grok-docs-11, grok-docs-16, grok-docs-35, grok-docs-40), which is core evidence for NL-command operation. However, hands-on community testing reports real trouble with agentic tool calling, saying the model 'hadn't been trained to think of tool calling as one of its primary modalities' (grok-comm-6), which tempers confidence that NL commands reliably trigger tool/connector actions. Missing for 10: independent benchmarks or user reports specifically confirming reliable NL-to-action execution across the built-in connectors, and no clear resolution of the tool-calling reliability concern.
- [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
- [claimed-docs] “Create new records - Add Leads, Opportunities, Accounts, Cases, or records on custom objects directly from chat.”
- [claimed-docs] “Search emails using Gmail search operators (`from:`, `to:`, `subject:`, `newer_than:`, `has:attachment`, etc.).”
- [claimed-docs] “Talk to Grok hands-free with voice.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [community] “I experimented with Grok 4 for openclaw... It was more verbally fluid than 5.5, but had real trouble with agentic tool calling - the model f…”
Api quality
ai-native userExplore an interactive API reference with runnable examples
weight 2 · round to GrokClaudenone0/10This evidence pack is entirely about Claude's consumer/product features (Cowork, connectors, memory, artifacts, etc.); there is no evidence of an interactive API reference with runnable examples. The probe explicitly found no OpenAPI spec at the checked endpoints, and no docs page describing an interactive API playground is present.
xAI publishes machine-readable docs (llms.txt, openapi.json) and a quickstart with example prompts/code, showing a structured API reference exists, but there is no evidence of an interactive 'try it now' console or in-browser runnable examples typical of tools like Swagger UI or Postman-style explorers. Missing for 10: interactive in-browser code execution/sandbox, live request/response try-it widget, independent confirmation of an interactive reference UI.
- [probe] “PROBE llms.txt: HTTP 200 at https://docs.x.ai/llms.txt # SpaceXAI API Documentation > Official SpaceXAI (xAI) developer documentation at ht…”
- [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”
- [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
- [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)
weight 2 · round to GrokClaudenone0/10The evidence pack includes explicit probes checking for a machine-readable API spec (openapi.json, swagger.json, etc.) on Claude's support domain, all returning 404, and no docs item anywhere references an OpenAPI/Swagger spec or downloadable schema for the Claude API. Nothing in the docs list an API reference format for AI-native consumption.
A direct probe confirms https://docs.x.ai/openapi.json returns HTTP 200 and contains an 'openapi' key, i.e., a downloadable, machine-readable OpenAPI spec for the xAI API, and this is corroborated by extensive first-party API docs describing the full endpoint surface (text, images, video, tools). Missing for 10: independent/community confirmation that developers actually consume this spec (e.g., via SDK codegen) beyond the automated probe.
- [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”
- [probe] “PROBE llms.txt: HTTP 200 at https://docs.x.ai/llms.txt # SpaceXAI API Documentation > Official SpaceXAI (xAI) developer documentation at ht…”
- [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
ai-native userTest against a sandbox environment without touching production data
weight 1 · round drawnClaudenone0/10The evidence pack shows Claude's connectors, Cowork, computer use, and browser automation acting directly on real accounts (Gmail, Drive, live websites) with no mention of a sandbox, staging, or test-mode environment that isolates actions from production data.
Groknone0/10No evidence of a sandbox/staging environment or test mode that isolates from production data; docs cover connectors, tunneling for custom tools, and general product features but nothing about a dedicated sandbox for testing without touching production data. missing for 10: sandbox/test environment documentation, data isolation guarantees, staging API keys or environments.
ai-native userRely on versioned APIs with a documented deprecation policy
weight 2 · round drawnClaudenone0/10The 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.
Groknone0/10The evidence shows model version slugs (grok-4.6, grok-4.5) and an OpenAPI spec, but no documentation of a formal deprecation policy, sunset timelines, or versioning guarantees for the API. Release notes describe new features and model updates but never state how/when older model versions are retired.
- [claimed-docs] “Grok 4.6, SpaceXAI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API. It has a 500k context wi…”
- [claimed-docs] “grok-4.6` and `grok-4.5` support the `reasoning_effort` parameter, which controls how much effort the model spends thinking before respondin…”
- [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”
Agents tasks — stories about agents tasks in this arenaAgents tasks
Stories about agents tasks in this arena
Agent mode
power-userDelegate a multi-step task that the assistant works on autonomously in the background and returns for my review
weight 3 · round to ClaudeClaude 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.”
Docs describe 'Grok Bot' as handing 'real work to AI teammates on a persistent cloud computer' and a 'Realtime Multi-agent Research' feature that orchestrates multi-step research autonomously, directly matching the story's core idea of background delegation and review. However, evidence is vendor-doc only with no independent confirmation of the async review workflow (notifications, task state, resuming), and community feedback (grok-comm-6) notes real trouble with agentic tool calling, suggesting reliability caveats. Missing for 10: independent hands-on validation of the background-task lifecycle, detail on how results are surfaced for review, and confirmation tool-calling reliability issues don't undermine multi-step autonomy.
- [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
- [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
- [community] “I experimented with Grok 4 for openclaw... It was more verbally fluid than 5.5, but had real trouble with agentic tool calling - the model f…”
- [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
power-userHave the assistant operate a web browser on my behalf to research and complete tasks on websites
weight 3 · round to ClaudeClaude 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.”
Groknone0/10The evidence shows connectors for APIs, email, calendar, Salesforce, and a vague 'Grok Bot' cloud computer teammate, but nothing documents Grok actually driving a web browser to navigate sites or complete tasks (no browsing/computer-use agent feature is described). Multi-agent research (grok-docs-26) is about research orchestration, not website interaction, so this applicable-but-unevidenced capability is 'none'.
- [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
power-userLet the assistant see and operate applications on my computer to complete work
weight 2 · round to ClaudeClaude 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.”
Groknone0/10Grok offers connectors (Gmail, Drive, Teams, Salesforce, custom MCP) and a 'Grok Bot' that operates on a persistent *cloud* computer, but there is no evidence of Grok seeing or controlling applications running on the user's own local machine/desktop (e.g., screen/GUI control akin to computer-use agents). Missing for 10: any documented local-computer screen/GUI control, first-party or hands-on evidence of operating a user's own desktop apps.
- [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
- [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [claimed-docs] “When you add a custom MCP connector, Grok's servers need to reach your MCP server over the public internet.”
Tasks
power-userSchedule recurring or one-off tasks that run automatically and come back to me with results
weight 2 · round to ClaudeClaude 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.”
Apps devices — stories about apps devices in this arenaApps devices
Stories about apps devices in this arena
Apps
power-userUse an official desktop app with OS-level shortcuts and access to what is on my screen
weight 2 · round to ClaudeClaude 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.”
Groknone0/10The evidence pack shows only cross-platform sign-in sync and hands-free voice, but no mention of an official desktop app with OS-level shortcuts or screen-reading/access capability; a community comment even notes the lack of a proper GUI for Grok's coding product ('still waiting for a proper gui for grok build ... codex desktop app is very useful'), suggesting no such desktop tool exists.
- [claimed-docs] “Sign in once and your conversations, settings, and subscription stay in sync across every platform.”
- [claimed-docs] “Talk to Grok hands-free with voice.”
- [community] “still waiting for a proper gui for grok build - terminal is nice but codex desktop app is very useful”
knowledge-workerUse full-featured official mobile apps for iOS and Android
weight 2 · round to ClaudeOfficial 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…”
Docs mention voice mode ('Talk to Grok hands-free with voice') and cross-platform sync of conversations/settings/subscriptions, implying mobile app support, but there is no explicit confirmation of dedicated full-featured iOS and Android apps, no app-store links, and no community/hands-on feedback about mobile app quality or feature parity with desktop/web. Missing for 10: explicit iOS/Android app documentation, feature-parity details, and independent user reviews of the mobile apps themselves.
- [claimed-docs] “Talk to Grok hands-free with voice.”
- [claimed-docs] “Sign in once and your conversations, settings, and subscription stay in sync across every platform.”
Custom bots
power-userBuild and share custom assistants with their own instructions and knowledge
weight 2 · round to ClaudeClaude 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.”
Groknone0/10The evidence pack covers connectors, tool integrations, MCP, image/video generation, and enterprise features, but there is no mention of a feature to create and share custom assistants/personas with their own instructions and knowledge base (akin to OpenAI's GPTs or Claude Projects).
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
ai-native userPerform bulk operations across many items at once
weight 2 · round to GrokClaudenone0/10The 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.
The docs mention batch generation of multiple images and support for up to 5 source images in a single edit, which is a narrow form of bulk operation, but there's no evidence of general-purpose bulk operations (e.g., bulk file processing, bulk record updates, batch text API) across many items or arbitrary data types. Missing for 10: a true batch/bulk API for text or file processing, bulk actions on connector data (e.g., mass email/calendar updates), and independent confirmation that these batch features work reliably at scale.
- [claimed-docs] “Generate images from text prompts with Grok Imagine models. The API supports batch generation of multiple images, and control over aspect ra…”
- [claimed-docs] “Image editing now accepts up to 5 source images per request (was 3).”
- [claimed-docs] “Use up to five source images for a single image edit.”
ai-native userDefine rules that trigger actions automatically on events
weight 3 · round to ClaudeClaude 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.”
Groknone0/10Grok's docs describe connectors, tool integrations, and a persistent 'Grok Bot' cloud agent, but nothing describes user-defined rules that trigger actions automatically on external events (e.g., webhooks, triggers, if-this-then-that automations, or scheduled event listeners). The axis is plausible for an AI-native product with tool/connector access, so this is 'none' rather than 'na'.
- [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
ai-native userSchedule recurring jobs or workflows
weight 2 · round to ClaudeClaude 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…”
ai-native userVersion, review, and roll back my automations
weight 1 · round drawnClaudenone0/10No 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.
Connectors apps — stories about connectors apps in this arenaConnectors apps
Stories about connectors apps in this arena
Connectors
power-userBrowse a directory of third-party apps and connectors and add them to the assistant
weight 2 · round to ClaudeClaude 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.”
Docs show Grok exposes a set of built-in, OAuth-authenticated connectors (Salesforce, Gmail, Google Calendar, Google Drive, Microsoft Teams) plus custom/MCP connectors that a user can add to reach external tools (grok-docs-16,19,35,36,37,2,3). This matches the 'add third-party apps/connectors' part of the story, but there's no explicit evidence of a browsable directory/marketplace UI, ratings, or a curated catalog page for discovering connectors. missing for 10: a documented directory/marketplace UI for browsing connectors, independent user confirmation of the browse experience.
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [claimed-docs] “Create new records - Add Leads, Opportunities, Accounts, Cases, or records on custom objects directly from chat.”
- [claimed-docs] “Search emails using Gmail search operators (`from:`, `to:`, `subject:`, `newer_than:`, `has:attachment`, etc.).”
- [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”
- [claimed-docs] “Search across channels and chats, read messages, send new messages, reply to threads, and create chats — all without leaving Grok.”
- [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
- [claimed-docs] “A tunneling service solves this by exposing your local server through a public URL that Grok can connect to.”
knowledge-workerConnect my cloud drive, email, and calendar so the assistant can search and use them in answers
weight 3 · round to ClaudeClaude 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…”
Grok docs explicitly describe built-in OAuth connectors for Gmail, Google Calendar, and Google Drive that let it search emails, read files, and manage calendar items right inside chat, plus a broader connectors framework for other SaaS tools. This directly matches the story of connecting cloud drive, email, and calendar for search/use in answers. Missing for 10: independent/hands-on confirmation of these specific connectors working reliably in practice (community evidence largely covers coding/chat quality, not connector behavior).
- [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [claimed-docs] “Search emails using Gmail search operators (`from:`, `to:`, `subject:`, `newer_than:`, `has:attachment`, etc.).”
- [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”
Files analysis — stories about files analysis in this arenaFiles analysis
Stories about files analysis in this arena
Analysis
power-userHave the assistant write and run code on my data to produce charts, computed answers, and downloadable files
weight 3 · round to ClaudeDocs 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.”
Groknone0/10The evidence describes Grok's coding assistant (Grok Build), connectors for email/calendar/files, image/video generation, and multi-agent research, but nothing documents a code-interpreter style capability where Grok writes and executes code against user-supplied data to produce charts, computed answers, or downloadable output files. Community comments discuss coding quality and agentic tool-calling issues but not this specific data-analysis/file-output workflow.
- [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
- [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
- [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”
- [community] “I experimented with Grok 4 for openclaw... It was more verbally fluid than 5.5, but had real trouble with agentic tool calling - the model f…”
Artifacts
knowledge-workerHave the assistant create and iteratively edit documents, presentations, and other files I can export
weight 2 · round to ClaudeDocs 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”
Groknone0/10The evidence pack shows Grok connectors for reading/searching Google Drive, Gmail, Calendar, and Salesforce, plus image/video generation and coding via Grok Build, but nothing describes a document/presentation authoring or iterative-editing feature (e.g., a canvas-style doc editor) with export to file formats like Word/PowerPoint/PDF.
- [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”
- [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
- [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
- [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
Files
knowledge-workerUpload documents, spreadsheets, and PDFs and get accurate analysis of their contents
weight 3 · round to ClaudeDocs 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”
Docs show Grok can ingest images and connect to Google Drive/Gmail to search and read files, and boasts a 500k context window for knowledge work, implying some document handling, but there is no explicit documentation of native PDF or spreadsheet upload/parsing in the core chat UI, nor any accuracy benchmarks or hands-on validation of document analysis. Missing for 10: explicit PDF/spreadsheet upload feature docs, accuracy testing/validation, independent user reports confirming reliable document analysis.
- [claimed-docs] “Grok 4.6, SpaceXAI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API. It has a 500k context wi…”
- [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
- [claimed-docs] “Some models allow images in the input. The model will consider the image context when generating the response.”
- [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”
Memory context — stories about memory context in this arenaMemory context
Stories about memory context in this arena
Memory
power-userHave the assistant remember relevant context from previous chats and apply it in new conversations
weight 3 · round to ClaudeClaude 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.”
Groknone0/10The evidence pack shows conversation storage (grok-docs-21) and cross-device sync of conversations/settings (grok-docs-41), but nothing describing a memory feature that recalls relevant context from past chats and applies it to new, unrelated conversations. No docs or community reports confirm persistent cross-chat memory recall.
power-userSet persistent custom instructions and preferences that shape every response
weight 1 · round to ClaudeClaude 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…”
Projects
knowledge-workerOrganize related chats and files into a project or space that shares context and instructions
weight 2 · round to ClaudeProjects 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”
Groknone0/10The evidence describes team 'workspaces' for licensing, SSO, and sharing conversations among teammates, plus connectors for external tools, but there is no mention of a project/space construct that groups related chats and files together with shared custom instructions or context, unlike dedicated 'Projects' features in other chat products.
- [claimed-docs] “In your team workspace, enjoy enterprise-grade privacy protections... Additionally, unlock the full capabilities of SuperGrok, including hig…”
- [claimed-docs] “Share conversations only with team members who have active licenses.”
- [claimed-docs] “Switch between workspaces to access team-specific features and ensure your conversations are protected under business plan terms.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
Multimodal — stories about multimodal in this arenaMultimodal
Stories about multimodal in this arena
Images
knowledge-workerGenerate and edit images from natural-language prompts
weight 2 · round to GrokClaude 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”
Grok Imagine and the API both explicitly support text-to-image generation and image editing (including multi-image edits up to 5 sources, aspect ratio control) with docs describing prompt-driven creation and editing directly relevant to knowledge-worker use. Missing for 10: independent hands-on community corroboration specifically of image generation/editing quality (community evidence pack focuses on coding/text/voice, not images).
- [claimed-docs] “Create images and video with Grok Imagine.”
- [claimed-docs] “Generate images from text prompts with Grok Imagine models. The API supports batch generation of multiple images, and control over aspect ra…”
- [claimed-docs] “Edit an existing image by providing a source image along with your prompt. The model understands the image content and applies your requeste…”
- [claimed-docs] “Use up to five source images for a single image edit.”
- [claimed-docs] “Image editing now accepts up to 5 source images per request (was 3).”
- [claimed-docs] “New aspect ratios. Image generation and editing accept 21:9 (cinematic widescreen) and 5:2 (wide banners).”
- [claimed-docs] “Requests to the slug will be served by grok-imagine-image-2.0 with quality set to low, with no change to the request or response shape”
knowledge-workerShare screenshots and photos and have the assistant accurately interpret what is in them
weight 2 · round drawnClaude'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”
Docs confirm image understanding is a first-class capability: models accept image input and 'consider the image context when generating the response' (grok-docs-25), plus related image editing docs show the model 'understands the image content' (grok-docs-29). No independent hands-on report specifically tests screenshot/photo interpretation accuracy. missing for 10: independent/community corroboration of accuracy on real screenshots or photos, detail on multi-image or OCR-style interpretation limits.
- [claimed-docs] “Some models allow images in the input. The model will consider the image context when generating the response.”
- [claimed-docs] “Edit an existing image by providing a source image along with your prompt. The model understands the image content and applies your requeste…”
- [claimed-docs] “Use up to five source images for a single image edit.”
Voice
knowledge-workerHave a natural, real-time voice conversation with the assistant
weight 2 · round to ClaudeClaude 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…”
xAI documents hands-free voice conversations directly in Grok ('Talk to Grok hands-free with voice') and separately documents real-time streaming speech-to-text with VAD tuning, indicating a live voice-conversation feature exists. However, missing for 10: independent/hands-on corroboration of voice conversation naturalness or latency, and no detail on turn-taking/interruption handling beyond the VAD parameter.
- [claimed-docs] “Talk to Grok hands-free with voice.”
- [claimed-docs] “Speech to Text now accepts a vad_threshold parameter (streaming query param and batch multipart field) to tune the voice-activity gate”
- [community] “I am excited for the voice mode promised in 'a week' or so. ChatGPT Advanced Voice has been a big disappointment for me... If Grok 3 voice m…”
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
ai-native userDo everything through the API that I can do in the UI
weight 2 · round to GrokClaudenone0/10The 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…”
The xAI API exposes core Grok model capabilities (text, images, video, tools, structured outputs, multi-agent research, connectors) documented alongside an OpenAPI spec, so much of the UI functionality is API-accessible. However, UI-only features like Grok Bot persistent cloud computer, team workspace/SSO/billing management, and built-in OAuth connectors (Gmail, Calendar, Teams, Salesforce) appear tied to the consumer/business app rather than exposed as general API endpoints, and there's no evidence of full parity. Missing for 10: confirmation that workspace/team management, SSO, billing, and native connector orchestration are API-accessible rather than UI-exclusive, plus independent corroboration of full feature parity.
- [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
- [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
- [claimed-docs] “Secure and streamline logins by integrating Single Sign-On (SSO) with your preferred Identity Provider (IdP).”
- [claimed-docs] “Visit grok.com/?_s=billing while logged in to manage your billing directly from the website (change plan, update payment, or cancel).”
- [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”
ai-native userExport all of my data in open formats and leave
weight 3 · round to ClaudeClaude 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.”
ai-native userRead the product's source under an open license
weight 2 · round drawnClaudenone0/10Claude is closed-source; there is no evidence of an open-license source release for the model or app, and community evidence even criticizes it as closed/opaque compared to FOSS alternatives like Codex CLI (claude-comm-6).
- [community] “Codex CLI is FOSS, unlike Claude Code, so Codex is less likely to do things like that, and it's one more reason to avoid Claude Code and Cla…”
Groknone0/10The evidence pack contains only proprietary API/product documentation and community commentary; there is no mention of any open-source license, public source repository, or open-weights release for Grok. As a mainstream capability question applicable to AI products, absence of evidence yields 'none' rather than 'na'.
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
ai-native userChoose where my data is stored (region/residency)
weight 2 · round drawnClaudenone0/10No 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.
Groknone0/10No evidence in the pack mentions data residency, region selection, or storage location choices for Grok; docs only confirm data is stored on xAI's servers without any residency options (grok-docs-21). Missing for 10: any mention of regional data storage options, residency controls, or compliance certifications tied to geography.
- [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”
ai-native userPrevent my data from being used to train AI models
weight 3 · round to ClaudeClaude 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.”
Groknone0/10The evidence pack documents data retention (prompts and responses stored on xAI's servers, grok-docs-21) and vague 'enterprise-grade privacy protections' for team workspaces (grok-docs-13), but nowhere mentions an opt-out toggle, training-data exclusion setting, or policy statement about excluding user conversations from model training. This axis clearly applies to a consumer/enterprise AI chat product, so absence of evidence yields 'none' rather than 'na'.
- [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”
- [claimed-docs] “In your team workspace, enjoy enterprise-grade privacy protections... Additionally, unlock the full capabilities of SuperGrok, including hig…”
- [claimed-docs] “Switch between workspaces to access team-specific features and ensure your conversations are protected under business plan terms.”
ai-native userControl data retention and deletion
weight 2 · round to ClaudeClaude 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…”
Groknone0/10Docs confirm that inputs, reasoning, and responses are stored on xAI's servers (grok-docs-21) and mention vague 'enterprise-grade privacy protections' for team workspaces (grok-docs-13), but there is no documented mechanism for users to view, control, or delete their stored data/conversation history. Missing for 10: explicit data retention settings, a user-facing deletion/export tool, and any policy detailing retention periods or opt-out controls.
- [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”
- [claimed-docs] “In your team workspace, enjoy enterprise-grade privacy protections... Additionally, unlock the full capabilities of SuperGrok, including hig…”
ai-native userOpt out of telemetry and usage tracking
weight 2 · round to ClaudeClaude 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.”
Groknone0/10The evidence pack confirms xAI stores prompts, reasoning, and responses on its servers (grok-docs-21) but contains no documentation of any telemetry/usage-tracking opt-out setting, privacy toggle, or data-collection preference control for individual or ai-native users.
- [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”
Research answers — stories about research answers in this arenaResearch answers
Stories about research answers in this arena
Research
knowledge-workerLaunch a deep research run that autonomously searches many sources and returns a cited report
weight 3 · round to ClaudeClaude'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.”
Grok's docs describe a dedicated 'Realtime Multi-agent Research' capability that orchestrates multiple AI agents to perform deep, multi-step research tasks, matching the core of the story [grok-docs-26]. However, the docs don't explicitly describe the output format (a cited report with sources) and there is no independent/hands-on corroboration of this specific feature in the evidence pack. Missing for 10: explicit documentation of citation/report formatting in the research output, and independent user validation that the feature works as described.
- [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
knowledge-workerGet answers grounded in current web results with citations back to the sources
weight 2 · round to ClaudeClaude'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.”
Evidence shows Grok has a 'Realtime Multi-agent Research' capability for deep, multi-step research tasks and community notes suggest it can discuss current events from live X/web data, implying some grounding, but nothing in the pack explicitly documents inline citations or source links back to web results in Grok's answers. missing for 10: explicit documentation of citation formatting/source links, first-party description of real-time web search grounding, and independent verification that citations are reliably attached to responses.
- [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
- [community] “I am excited for the voice mode promised in 'a week' or so. ChatGPT Advanced Voice has been a big disappointment for me... If Grok 3 voice m…”
Trust controls — stories about trust controls in this arenaTrust controls
Stories about trust controls in this arena
Admin
team-adminManage members, permissions, and data policies for my organization's workspace
weight 2 · round to GrokEvidence 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…”
Docs show a business/team workspace admin story: inviting members via email (grok-docs-18), SSO integration with IdP (grok-docs-17), workspace switching with business-plan-protected conversations (grok-docs-39), license-gated sharing (grok-docs-14), and 'enterprise-grade privacy protections' (grok-docs-13). This covers member invitation, authentication/SSO, and some data-policy framing for admins. Missing for 10: detailed role/permission granularity (e.g., admin vs member roles, per-connector access control), explicit data retention/DLP policy configuration UI, and any independent/community corroboration of the admin console working as documented.
- [claimed-docs] “Secure and streamline logins by integrating Single Sign-On (SSO) with your preferred Identity Provider (IdP).”
- [claimed-docs] “Invite new team members to join your Grok Business workspace with a simple email invitation process.”
- [claimed-docs] “Switch between workspaces to access team-specific features and ensure your conversations are protected under business plan terms.”
- [claimed-docs] “Share conversations only with team members who have active licenses.”
- [claimed-docs] “In your team workspace, enjoy enterprise-grade privacy protections... Additionally, unlock the full capabilities of SuperGrok, including hig…”
Data controls
knowledge-workerExport my complete chat history and account data
weight 1 · round to ClaudeClaude'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…”
Groknone0/10No evidence in the pack mentions a data export or account-data download feature for Grok; docs cover connectors, models, billing, SSO, and workspace features but never a 'export my chat history/data' capability. This is a fair trust-controls axis for a consumer chat product, so absence of evidence yields 'none' rather than 'na'.
knowledge-workerControl whether my conversations are used to train models
weight 3 · round to ClaudeClaude 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.”
Groknone0/10Docs mention 'enterprise-grade privacy protections' for team workspaces and that prompts are stored on xAI servers, but there is no documented setting or toggle letting a knowledge-worker control whether their conversations are used to train models. Community commentary raises general distrust but does not confirm or deny a specific training opt-out control.
- [claimed-docs] “In your team workspace, enjoy enterprise-grade privacy protections... Additionally, unlock the full capabilities of SuperGrok, including hig…”
- [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”
- [community] “Musk already has too much power, won't trust him with my AI conversations.”
Not comparable on these axes
ai-native userConnect an agent via an official MCP server
weight 3 · not comparableClauden/aClaude is itself an AI agent/assistant (client role); the evidence only shows Claude connecting to or building remote MCP servers as a client (claude-docs-18, claude-docs-31, claude-docs-36, claude-probe-4), which is the separate MCP-client story. There is no evidence Claude itself runs as an MCP server that other agents could connect to, so this server-role axis does not apply to this product.
Grokn/aGrok is itself an agent/assistant (chat + Grok Build coding agent), and the MCP-related evidence (grok-docs-2,3,19,38) describes Grok acting as an MCP *client* connecting outbound to a user's custom MCP server — not Grok exposing itself as an MCP server for other agents to connect to. Per the rules, client-side MCP connectivity does not make this server-role axis applicable, and there is no evidence of a first-party 'Grok as MCP server' endpoint.
- [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
- [claimed-docs] “A tunneling service solves this by exposing your local server through a public URL that Grok can connect to.”
- [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
- [claimed-docs] “When you add a custom MCP connector, Grok's servers need to reach your MCP server over the public internet.”
ai-native userSelf-host the core product
weight 3 · not comparableClauden/aClaude is a closed, hosted proprietary model/service with no self-hosting option; self-hosting the core product is a category error for this type of SaaS/AI assistant offering, not an unmet applicable axis.
Groknone0/10Grok is a closed, proprietary API/cloud service; no evidence anywhere in the pack of open-sourced weights or a self-hostable core model/product, only hosted APIs, connectors, and SaaS features. Absence of any self-hosting capability for an applicable axis (models can in principle be released for self-hosting, as some competitors do) yields none rather than na.
- [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
- [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”
- [claimed-docs] “Visit grok.com/?_s=billing while logged in to manage your billing directly from the website (change plan, update payment, or cancel).”