# GUI Agent Interaction on MobileWorld GUI-Only Source: [GUI Agent Interaction on MobileWorld GUI-Only]() Collection index: [llms.txt]() Data updated: 2026-04-14T12:34:55.127Z Evaluation of GUI Agent Interaction performance on the MobileWorld GUI-Only dataset, measured by Success Rate (SR). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | GUI Agent Interaction | | Dataset (including any stated split) | MobileWorld GUI-Only | | Metric | SR | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [SR](): Higher is better; unit: PERCENT. ## Recorded results | Method | SR | Result date | Report paper | | --- | --- | --- | --- | | Gemini-3-Pro + UI-Ins-7B | 55.6 | Not recorded | 69ddca847d0172140ec7a037 | | GPT-5 + UI-Ins-7B | 54 | Not recorded | 69ddca847d0172140ec7a037 | | Claude-4.5-Sonnet + UI-Ins-7B | 47.8 | Not recorded | 69ddca847d0172140ec7a037 | | Doubao-1.5-UI-TARS | 26.3 | Not recorded | 69ddca847d0172140ec7a037 | | MAI-UI-8B | 19.7 | Not recorded | 69ddca847d0172140ec7a037 | | ClawGUI-2B | 17.1 | Not recorded | 69ddca847d0172140ec7a037 | | UI-Venus-72B | 16.4 | Not recorded | 69ddca847d0172140ec7a037 | | Qwen3-VL-235B-A22B | 12.8 | Not recorded | 69ddca847d0172140ec7a037 | | Qwen3-VL-32B | 11.9 | Not recorded | 69ddca847d0172140ec7a037 | | MAI-UI-2B | 11.1 | Not recorded | 69ddca847d0172140ec7a037 | | Qwen3-VL-8B | 9.4 | Not recorded | 69ddca847d0172140ec7a037 | | GUI-Owl-32B | 8.5 | Not recorded | 69ddca847d0172140ec7a037 | | UI-Venus-7B | 8.5 | Not recorded | 69ddca847d0172140ec7a037 | | GUI-Owl-7B | 7.7 | Not recorded | 69ddca847d0172140ec7a037 | ### Gemini-3-Pro + UI-Ins-7B SR: 55.6. Result ID: 69de345b47f34ce924c714be. [Reporting paper]() Recorded evaluation configuration: {"Framework Type":"Agentic Framework"}. This record does not assert independent reproduction. ### GPT-5 + UI-Ins-7B SR: 54. Result ID: 69de345b47f34ce924c714bf. [Reporting paper]() Recorded evaluation configuration: {"Framework Type":"Agentic Framework"}. This record does not assert independent reproduction. ### Claude-4.5-Sonnet + UI-Ins-7B SR: 47.8. Result ID: 69de345b47f34ce924c714bd. [Reporting paper]() Recorded evaluation configuration: {"Framework Type":"Agentic Framework"}. This record does not assert independent reproduction. ### Doubao-1.5-UI-TARS SR: 26.3. Result ID: 69de345b47f34ce924c714c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework Type":"End-to-End Model"}. This record does not assert independent reproduction. ### MAI-UI-8B SR: 19.7. Result ID: 69de345b47f34ce924c714c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework Type":"End-to-End Model"}. This record does not assert independent reproduction. ### ClawGUI-2B SR: 17.1. Result ID: 69de345b47f34ce924c714ca. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Framework Type":"Ours"}. This record does not assert independent reproduction. ### UI-Venus-72B SR: 16.4. Result ID: 69de345b47f34ce924c714c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework Type":"End-to-End Model"}. This record does not assert independent reproduction. ### Qwen3-VL-235B-A22B SR: 12.8. Result ID: 69de345b47f34ce924c714c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework Type":"End-to-End Model"}. This record does not assert independent reproduction. ### Qwen3-VL-32B SR: 11.9. Result ID: 69de345b47f34ce924c714c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework Type":"End-to-End Model"}. This record does not assert independent reproduction. ### MAI-UI-2B SR: 11.1. Result ID: 69de345b47f34ce924c714c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework Type":"End-to-End Model"}. This record does not assert independent reproduction. ### Qwen3-VL-8B SR: 9.4. Result ID: 69de345b47f34ce924c714c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework Type":"End-to-End Model"}. This record does not assert independent reproduction. ### GUI-Owl-32B SR: 8.5. Result ID: 69de345b47f34ce924c714c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework Type":"End-to-End Model"}. This record does not assert independent reproduction. ### UI-Venus-7B SR: 8.5. Result ID: 69de345b47f34ce924c714c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework Type":"End-to-End Model"}. This record does not assert independent reproduction. ### GUI-Owl-7B SR: 7.7. Result ID: 69de345b47f34ce924c714c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework Type":"End-to-End Model"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.