MobileMiniWoB++
Qwen2.5-VL-72B 68% Dropped Agents complete MiniWoB++ web tasks inside the Android emulator of AndroidWorld. Scored by task success rate.
Runs as the miniwob suite of AndroidWorld. MiniWoB++ itself comes from Liu et al. 2018.
Made by Google Research (AndroidWorld team) Released May 2024 Phones All tasks public Last in a launch post Jan 2025 , dropped before it saturated
Last model added Feb 2025
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
1
Model scored in lab cards
1
Launch post lists it, from 1 lab
1
System card reports it, from 1 lab
Qwen2.5-VL-72B leads with 68%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen2.5-VL-72B | 68% | Jan 2025 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Reported by the lab in its model card
No launch post has listed it since Jan 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 28 Jan 2025 | Qwen2.5-VL-72B | 68 | MobileMiniWob++_SR |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 19 Feb 2025 | Qwen2.5-VL-72B technical report | 68 | MobileMiniWob++ SR (Table 9) | Capabilities |
More in Computer and browser use
- BrowseComp In use Hard-to-find facts that need persistent web browsing. Short verifiable answers graded for exact correctness. Claude Fable 5 93.3%
- ScreenSpot-Pro In use GUI grounding on high-resolution professional-software screenshots. The model must locate the target UI element. GPT-6 Astra 92.7%
- AndroidWorld In use Agents complete 116 tasks across 20 real Android apps in an emulator. Each task checks the device's system state to judge success. GPT-6 Astra 100%
- OSWorld 2.1 In use Agents complete 108 long-horizon workflows across 31 self-hosted websites and desktop apps, averaging 318 tool calls. Scored by binary completion and checkpoint partial credit. Claude Opus 5.5 81.8%
- WebArena-Verified In use Agents complete 812 audited WebArena tasks on self-hosted websites. Deterministic evaluators check the agent's answer and captured network traces.
Muse Spark 1.1 69% - MobileWorld In use Agents complete 201 tasks across 20 mobile apps, including tasks that need user clarification or MCP tools. Backend checks verify success. Kimi K3 74.4%