# Person Relation on Personal-VCL-Bench Persons

Source: [Person Relation on Personal-VCL-Bench Persons](<https://www.sota2.com/research/sota/person-relation-on-personal-vcl-bench-persons>)

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

Data updated: 2026-05-12T17:05:08.941Z

Evaluation of model performance on determining person relations using the Personal-VCL-Bench Persons dataset, measured by 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 | Person Relation |
| Dataset (including any stated split) | Personal-VCL-Bench Persons |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/person-relation-on-personal-vcl-bench-persons.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Agentic Context Bank | 51.2 | Not recorded | 6a02b4b5dbc836b87d824fd0 |
| Language-ctx (kmax) | 49.6 | Not recorded | 6a02b4b5dbc836b87d824fd0 |
| Visual-ctx (kmax) | 46.4 | Not recorded | 6a02b4b5dbc836b87d824fd0 |
| No-context | 22.4 | Not recorded | 6a02b4b5dbc836b87d824fd0 |

### Agentic Context Bank

Accuracy: 51.2. Result ID: 6a035daa47f34ce924e9071e.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b4b5dbc836b87d824fd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b4b5dbc836b87d824fd0.md>)

Recorded evaluation configuration: {"Context regime":"Ours","Backbone":"Gemma-4-31B"}. This record does not assert independent reproduction.

### Language-ctx (kmax)

Accuracy: 49.6. Result ID: 6a035daa47f34ce924e9071c.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b4b5dbc836b87d824fd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75261e209131cea6629c.md>)

[Implementation](<https://github.com/CeeZh/LLoVi>)

Recorded evaluation configuration: {"Context regime":"Language-ctx (kmax)","Backbone":"Gemma-4-31B"}. This record does not assert independent reproduction.

### Visual-ctx (kmax)

Accuracy: 46.4. Result ID: 6a035daa47f34ce924e9071d.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b4b5dbc836b87d824fd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b01e209131cea74bb6.md>)

Recorded evaluation configuration: {"Context regime":"Visual-ctx (kmax)","Backbone":"Gemma-4-31B"}. This record does not assert independent reproduction.

### No-context

Accuracy: 22.4. Result ID: 6a035daa47f34ce924e9071b.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b4b5dbc836b87d824fd0.md>)

Recorded evaluation configuration: {"Context regime":"No-context","Backbone":"Gemma-4-31B"}. This record does not assert independent reproduction.

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