# Element Grounding on Multimodal-Mind2Web Cross-Website

Source: [Element Grounding on Multimodal-Mind2Web Cross-Website](<https://www.sota2.com/research/sota/element-grounding-on-multimodal-mind2web-cross-website>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:41:56.641Z

Evaluation of Element Grounding performance on the Multimodal-Mind2Web Cross-Website 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-Website |
| Metric | Element Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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](<https://www.sota2.com/research/sota/element-grounding-on-multimodal-mind2web-cross-website.md?metric=Element%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Element Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| UGround-V1-7B | 48.1 | Not recorded | 68fa79851e209131cea7dfab |
| UGround-V1-2B | 47.6 | Not recorded | 68fa79851e209131cea7dfab |
| UGround | 46 | Not recorded | 68fa79851e209131cea7dfab |
| UGround | 44.7 | Not recorded | 68fa79851e209131cea7dfab |
| Choice | 38 | Not recorded | 68fa79851e209131cea7dfab |
| SeeClick | 33.1 | Not recorded | 68fa79851e209131cea7dfab |
| SeeClick | 28.5 | Not recorded | 68fa79851e209131cea7dfab |
| SoM | 20.1 | Not recorded | 68fa79851e209131cea7dfab |

### UGround-V1-7B

Element Accuracy: 48.1. Result ID: 698b51ee8d67a41d0a6d0f3b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Implementation](<https://osu-nlp-group.github.io/UGround/>)

Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction.

### UGround-V1-2B

Element Accuracy: 47.6. Result ID: 698b51ee8d67a41d0a6d0f3a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Implementation](<https://osu-nlp-group.github.io/UGround/>)

Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction.

### UGround

Element Accuracy: 46. Result ID: 698b51ee8d67a41d0a6d0f39.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Implementation](<https://osu-nlp-group.github.io/UGround/>)

Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction.

### UGround

Element Accuracy: 44.7. Result ID: 698b51ee8d67a41d0a6d0f37.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Implementation](<https://osu-nlp-group.github.io/UGround/>)

Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4"}. This record does not assert independent reproduction.

### Choice

Element Accuracy: 38. Result ID: 698b51ee8d67a41d0a6d0f34.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72821e209131cea56e28.md>)

Recorded evaluation configuration: {"Input":"Image + Text","Planner":"GPT-4"}. This record does not assert independent reproduction.

### SeeClick

Element Accuracy: 33.1. Result ID: 698b51ee8d67a41d0a6d0f38.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72441e209131cea55627.md>)

[Implementation](<https://github.com/njucckevin/SeeClick>)

Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction.

### SeeClick

Element Accuracy: 28.5. Result ID: 698b51ee8d67a41d0a6d0f36.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72441e209131cea55627.md>)

[Implementation](<https://github.com/njucckevin/SeeClick>)

Recorded evaluation configuration: {"Input":"Image (SeeAct-V)","Planner":"GPT-4"}. This record does not assert independent reproduction.

### SoM

Element Accuracy: 20.1. Result ID: 698b51ee8d67a41d0a6d0f35.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72821e209131cea56e28.md>)

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.