Tabbit
ResourcesBlogModels
Tabbit LogoTabbit

Tabbit — The AI Browser that Works for You

Topics

  • Best Browsers 2026: Rankings and Top Lists
  • AI Browser Guides and Resources
  • Browser Comparisons: Head-to-Head Guides
  • Browser Reviews and Explainers
  • Browser Alternatives
  • Browser Directory: Guides by Browser
  • Agentic Browser Resources
  • Browser Downloads and Install Guides
  • Browser Productivity Resources
  • SillyTavern Model Guides and Presets

Popular Guides

  • Best Browsers 2026: Top 10 Ranked & Compared
  • Best Free AI Browsers 2026: Plans & Prices Compared
  • Rabbit Browser: What It Is & Why Tabbit Is Better
  • Firefox vs Chrome 2026: Privacy, RAM & Speed Compared
  • Best Lightweight Browsers 2026: 7 Tested for RAM & Speed
  • AI Browser List 2026: 10 Browsers Compared
  • Neobrowser: Norton Neo, Download & Alternatives
  • Edge vs Chrome 2026: Speed, RAM & Battery Tested
  • Best Internet Browser for Android 2026
  • Best AI Browser 2026: Top 9 Tested & Ranked

Events

  • Tabbit Skill Competition
  • KPOP SBTI Fandom Personality Test
  • Tabbit Campus Creator Program
  • fifi's Picks: AI Skills for Research Papers
  • User Survey

About

  • Tabbit Blog
  • Press & Media
English
简体中文English
Showcases & prompts
MediaHy4

Hy4 Vision Understanding and Cross-App Workflow: A Hands-On Test

Original source

Kr (contributed by LeiTech and published with permission)

AuthorLeiTech (guest contributor; no individual author is listed on the page)

Source date2026-11-05

Tabbit curation2026-11-05

Read original

One-sentence takeaway

LeiTech says it used Hy4 in WorkBuddy to operate WeChat and check local files. The model extracted a visa document checklist from chat history, inspected the Downloads folder, and identified missing items. The article includes the task prompt and a description of the result.

Use cases

  • Suitable tasks: Finding information across apps, reading on-screen content, and checking it against local files with the user's authorization.

  • Unsuitable tasks: Judging accuracy and safety across all apps, accounts, or complex workflows based on a single media test.

  • Applicable model version: Tencent Hunyuan Hy4.

  • Applicable client, agent, or API: WorkBuddy; the article says it used computer control to read the WeChat interface and a local folder.

  • Recommended reasoning level and parameters: Not specified in the article.

Ready-to-use content

The following is the case prompt published in the article. Replace the scenario and file locations according to the actual scope of authorization:

最近我在办理西班牙签证,已经微信添加旅行社工作人员并对接。你查询下微信聊天记录(微信已登录,可用Computer Use来操作),看看要提供哪些资料。另外,我在Mac本地下载文件夹里存放了护照扫描件和户口本电子页PDF文件,你核对下,看我还… This is a necessary excerpt; read the original source for full context.

English translation for reuse:

I'm applying for a Spanish visa and have already added and contacted the travel agency staff member on WeChat. Please ch… This is a necessary excerpt; read the original source for full context.

This prompt is quoted from the case study; it is not a general operating procedure for other apps.

Test or workflow steps

  1. Select Hy4 in WorkBuddy and confirm that WeChat is logged in.

  2. Ask the model to extract the travel agency's document requirements from the specified WeChat chat.

  3. Ask the model to check the existing files in the local Downloads folder against the document checklist.

  4. Review the missing-item assessment and its reasoning; confirm sensitive operations when prompted by the app.

The article says Hy4 found the travel agency staff member and the document requirements in the chat, then checked local files and identified the documents that were still missing. It also found that an existing U.S. visa photo could not directly substitute for a Schengen visa photo.

Original evidence and data

  • The original task explicitly asks the model to check WeChat chat history, inspect the local Mac Downloads folder, and lists an existing passport scan and household register PDF.

  • The article describes the process as computer control and a cross-app task, and says the model first retrieved information from WeChat, then checked local files.

  • The same article also reports another vision case: Hy4 was given a screenshot of Apple's Q4 financial report and the prompt, “Based on this screenshot of Apple's Q4 report, calculate the iPhone ASP (average selling price) for the quarter.” The article says it extracted revenue, searched online for shipment volume, and calculated an ASP of $1,005. This result and its accuracy are reported by the media and were not independently verified here.

  • The original states, “This article is from ‘LeiTech’ and is published by 36Kr with permission.” The page credits “LeiTech · Guest Contributor” and does not name an individual author. These results are a single media-reported experience, not an independently reproduced experiment.

Limitations

  • The case depends on WorkBuddy's computer-control capabilities, a logged-in WeChat account, and access to local files. It does not establish that Hy4 alone can complete the same steps through an API.

  • The original provides no screen recording, complete execution log, or downloadable output file, so the recognition process and final checklist cannot be independently verified step by step.

  • Before processing real chats or identity documents, confirm access authorization and review the requirements extracted by the model. Do not paste account credentials or the contents of identity documents into the prompt.

Reproduction notes

In an authorized test environment, prepare simulated chat history and non-real identity document samples, then use the task structure from the article to separately check extraction of chat requirements, file recognition, and missing-item assessment. Record the client version, model selection, permission confirmations, input materials, and output. Label local reproduction results separately from the media report in the original.

Curated by Tabbit

Prompts and showcases are summarized from public sources and Tabbit editorial notes. Check the original licensing and intended use before copying it.

Hy4

Use in Tabbit

Hy4

Related showcases & prompts

OfficialTencent Cloud Model-as-a-Service TokenHub documentation

Tencent Cloud TokenHub: Hy4 GA Model ID, Reasoning, and Multimodal Parameters

OfficialOpenRouter model page and API configuration panel

OpenRouter: Hy4 Production Model API and Routing Configuration

OfficialOpenClaw documentation

Explicitly Select the Tencent Hunyuan Hy4 GA in OpenClaw

OfficialTencent Cloud TokenHub documentation

Connect Tencent Cloud Hy4 to OpenCode

Hy4

Related reviews

OfficialTencent Hunyuan official website, “Research”2026-11-04

Tencent Hunyuan: Hy4 Stable Release and Benchmark Results

MediaMercor APEX

Mercor APEX-Agents Professional Task Benchmark: Hy4 High Score Snapshot

MediaVals AI

Vals AI: Hy4's Cross-domain Results on Vals Index

MediaPlotly official blog2026-11-04

Plotly: Tencent Hunyuan Hy4 Data Analytics Benchmark