# Element Grounding on Multimodal-Mind2Web Cross-Task Source: [Element Grounding on Multimodal-Mind2Web Cross-Task]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:56.676Z Evaluation of Element Grounding performance on the Multimodal-Mind2Web Cross-Task dataset, typically measured using Element Accuracy. 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 | Element Grounding | | Dataset (including any stated split) | Multimodal-Mind2Web Cross-Task | | Metric | Element Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Element Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Element Accuracy | Result date | Report paper | | --- | --- | --- | --- | | UGround-V1-7B | 50.7 | Not recorded | 68fa79851e209131cea7dfab | | UGround-V1-2B | 48.6 | Not recorded | 68fa79851e209131cea7dfab | | UGround-V1-7B | 48.5 | Not recorded | 68fa79851e209131cea7dfab | | UGround | 47.7 | Not recorded | 68fa79851e209131cea7dfab | | UGround-V1-2B | 47.7 | Not recorded | 68fa79851e209131cea7dfab | | UGround | 46.6 | Not recorded | 68fa79851e209131cea7dfab | | Choice | 46.4 | Not recorded | 68fa79851e209131cea7dfab | | UGround | 45.1 | Not recorded | 68fa79851e209131cea7dfab | | UGround | 44.6 | Not recorded | 68fa79851e209131cea7dfab | | Choice | 42.4 | Not recorded | 68fa79851e209131cea7dfab | | SeeClick | 33.5 | Not recorded | 68fa79851e209131cea7dfab | | SeeClick | 32.1 | Not recorded | 68fa79851e209131cea7dfab | | SeeClick | 30.7 | Not recorded | 68fa79851e209131cea7dfab | | SeeClick | 29.7 | Not recorded | 68fa79851e209131cea7dfab | | SoM | 29.6 | Not recorded | 68fa79851e209131cea7dfab | | SoM | 27 | Not recorded | 68fa79851e209131cea7dfab | ### UGround-V1-7B Element Accuracy: 50.7. Result ID: 698b51ee8d67a41d0a6d0f33. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction. ### UGround-V1-2B Element Accuracy: 48.6. Result ID: 698b51ee8d67a41d0a6d0f32. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction. ### UGround-V1-7B Element Accuracy: 48.5. Result ID: 698c52c237894ef7d9cd7ffe. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction. ### UGround Element Accuracy: 47.7. Result ID: 698b51ee8d67a41d0a6d0f31. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction. ### UGround-V1-2B Element Accuracy: 47.7. Result ID: 698c52c237894ef7d9cd7ffd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction. ### UGround Element Accuracy: 46.6. Result ID: 698c52c237894ef7d9cd7ffc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction. ### Choice Element Accuracy: 46.4. Result ID: 698b51ee8d67a41d0a6d0f2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Image + Text","Planner":"GPT-4"}. This record does not assert independent reproduction. ### UGround Element Accuracy: 45.1. Result ID: 698b51ee8d67a41d0a6d0f2f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4"}. This record does not assert independent reproduction. ### UGround Element Accuracy: 44.6. Result ID: 698c52c237894ef7d9cd7ffa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4"}. This record does not assert independent reproduction. ### Choice Element Accuracy: 42.4. Result ID: 698c52c237894ef7d9cd7ff7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Image + Text","Planner":"GPT-4"}. This record does not assert independent reproduction. ### SeeClick Element Accuracy: 33.5. Result ID: 698c52c237894ef7d9cd7ffb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction. ### SeeClick Element Accuracy: 32.1. Result ID: 698b51ee8d67a41d0a6d0f30. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction. ### SeeClick Element Accuracy: 30.7. Result ID: 698c52c237894ef7d9cd7ff9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4"}. This record does not assert independent reproduction. ### SeeClick Element Accuracy: 29.7. Result ID: 698b51ee8d67a41d0a6d0f2e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4"}. This record does not assert independent reproduction. ### SoM Element Accuracy: 29.6. Result ID: 698b51ee8d67a41d0a6d0f2d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Image + Text","Planner":"GPT-4"}. This record does not assert independent reproduction. ### SoM Element Accuracy: 27. Result ID: 698c52c237894ef7d9cd7ff8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input":"Image + Text","Planner":"GPT-4"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.