# GUI Navigation on MMG2Skill-Bench GUI Source: [GUI Navigation on MMG2Skill-Bench GUI]() Collection index: [llms.txt]() Data updated: 2026-06-02T12:37:31.830Z Evaluation of agent performance on GUI Navigation tasks using the MMG2Skill-Bench GUI dataset, measured by metrics such as Success Rate. 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 Navigation | | Dataset (including any stated split) | MMG2Skill-Bench GUI | | Metric | Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | MMG2Skill | 77.25 | Not recorded | 6a1e6443dbd7150506f85913 | | Raw Guide | 74.75 | Not recorded | 6a1e6443dbd7150506f85913 | | Vanilla | 69.75 | Not recorded | 6a1e6443dbd7150506f85913 | | MMG2Skill | 64.75 | Not recorded | 6a1e6443dbd7150506f85913 | | Vanilla | 62.22 | Not recorded | 6a1e6443dbd7150506f85913 | | MMG2Skill | 59.76 | Not recorded | 6a1e6443dbd7150506f85913 | | Raw Guide | 59.75 | Not recorded | 6a1e6443dbd7150506f85913 | | MMG2Skill | 57.24 | Not recorded | 6a1e6443dbd7150506f85913 | | Vanilla | 49.76 | Not recorded | 6a1e6443dbd7150506f85913 | | Raw Guide | 47.5 | Not recorded | 6a1e6443dbd7150506f85913 | | MMG2Skill | 39.99 | Not recorded | 6a1e6443dbd7150506f85913 | | Vanilla | 39.74 | Not recorded | 6a1e6443dbd7150506f85913 | | Raw Guide | 37.24 | Not recorded | 6a1e6443dbd7150506f85913 | | MMG2Skill | 35 | Not recorded | 6a1e6443dbd7150506f85913 | | Raw Guide | 19.99 | Not recorded | 6a1e6443dbd7150506f85913 | | Vanilla | 19.97 | Not recorded | 6a1e6443dbd7150506f85913 | | Raw Guide | 17.5 | Not recorded | 6a1e6443dbd7150506f85913 | | Vanilla | 15 | Not recorded | 6a1e6443dbd7150506f85913 | ### MMG2Skill Success Rate: 77.25. Result ID: 6a1ece13fbc373592c1a857b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Kimi-K2.6","Prompting Variant":"MMG2Skill"}. This record does not assert independent reproduction. ### Raw Guide Success Rate: 74.75. Result ID: 6a1ece13fbc373592c1a857a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Kimi-K2.6","Prompting Variant":"Raw Guide"}. This record does not assert independent reproduction. ### Vanilla Success Rate: 69.75. Result ID: 6a1ece13fbc373592c1a8579. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Kimi-K2.6","Prompting Variant":"Vanilla"}. This record does not assert independent reproduction. ### MMG2Skill Success Rate: 64.75. Result ID: 6a1ece13fbc373592c1a8572. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Claude-Opus-4.6","Prompting Variant":"MMG2Skill"}. This record does not assert independent reproduction. ### Vanilla Success Rate: 62.22. Result ID: 6a1ece13fbc373592c1a8570. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Claude-Opus-4.6","Prompting Variant":"Vanilla"}. This record does not assert independent reproduction. ### MMG2Skill Success Rate: 59.76. Result ID: 6a1ece13fbc373592c1a8578. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Claude-Sonnet-4.6","Prompting Variant":"MMG2Skill"}. This record does not assert independent reproduction. ### Raw Guide Success Rate: 59.75. Result ID: 6a1ece13fbc373592c1a8571. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Claude-Opus-4.6","Prompting Variant":"Raw Guide"}. This record does not assert independent reproduction. ### MMG2Skill Success Rate: 57.24. Result ID: 6a1ece13fbc373592c1a8575. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-5.5","Prompting Variant":"MMG2Skill"}. This record does not assert independent reproduction. ### Vanilla Success Rate: 49.76. Result ID: 6a1ece13fbc373592c1a8576. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Claude-Sonnet-4.6","Prompting Variant":"Vanilla"}. This record does not assert independent reproduction. ### Raw Guide Success Rate: 47.5. Result ID: 6a1ece13fbc373592c1a8577. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Claude-Sonnet-4.6","Prompting Variant":"Raw Guide"}. This record does not assert independent reproduction. ### MMG2Skill Success Rate: 39.99. Result ID: 6a1ece13fbc373592c1a8581. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Prompting Variant":"MMG2Skill"}. This record does not assert independent reproduction. ### Vanilla Success Rate: 39.74. Result ID: 6a1ece13fbc373592c1a8573. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-5.5","Prompting Variant":"Vanilla"}. This record does not assert independent reproduction. ### Raw Guide Success Rate: 37.24. Result ID: 6a1ece13fbc373592c1a8574. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-5.5","Prompting Variant":"Raw Guide"}. This record does not assert independent reproduction. ### MMG2Skill Success Rate: 35. Result ID: 6a1ece13fbc373592c1a857e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemini-3.1-Pro-Preview","Prompting Variant":"MMG2Skill"}. This record does not assert independent reproduction. ### Raw Guide Success Rate: 19.99. Result ID: 6a1ece13fbc373592c1a857d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Gemini-3.1-Pro-Preview","Prompting Variant":"Raw Guide"}. This record does not assert independent reproduction. ### Vanilla Success Rate: 19.97. Result ID: 6a1ece13fbc373592c1a857c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Gemini-3.1-Pro-Preview","Prompting Variant":"Vanilla"}. This record does not assert independent reproduction. ### Raw Guide Success Rate: 17.5. Result ID: 6a1ece13fbc373592c1a8580. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Prompting Variant":"Raw Guide"}. This record does not assert independent reproduction. ### Vanilla Success Rate: 15. Result ID: 6a1ece13fbc373592c1a857f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3.6-Plus","Prompting Variant":"Vanilla"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.