# Visual Entity Disambiguation on MELBench (test)

Source: [Visual Entity Disambiguation on MELBench (test)](<https://www.sota2.com/research/sota/visual-entity-disambiguation-on-melbench-test>)

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

Data updated: 2026-02-26T05:43:15.500Z

Evaluation of Visual Entity Disambiguation performance on the test split of the MELBench dataset, measured using F1 score.

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 | Visual Entity Disambiguation |
| Dataset (including any stated split) | MELBench (test) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/visual-entity-disambiguation-on-melbench-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| GDMM-large | 72.41 | Not recorded | 68fa6f781e209131cea45c8e |
| GDMM-base | 68.01 | Not recorded | 68fa6f781e209131cea45c8e |
| Gan et al. | 40.5 | Not recorded | 68fa6f781e209131cea45c8e |

### GDMM-large

F1 Score: 72.41. Result ID: 6990d6173a6c31484903a82f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f781e209131cea45c8e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f781e209131cea45c8e.md>)

Recorded evaluation configuration: {"Modality":"LV -\> L","Model Scale":"large"}. This record does not assert independent reproduction.

### GDMM-base

F1 Score: 68.01. Result ID: 6990d6173a6c31484903a82e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f781e209131cea45c8e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f781e209131cea45c8e.md>)

Recorded evaluation configuration: {"Modality":"LV -\> L","Model Scale":"base"}. This record does not assert independent reproduction.

### Gan et al.

F1 Score: 40.5. Result ID: 6990d6173a6c31484903a82d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f781e209131cea45c8e.md>)

Recorded evaluation configuration: {"Modality":"LV -\> L"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.