# Visual Question Answering on GLI (val)

Source: [Visual Question Answering on GLI (val)](<https://www.sota2.com/research/sota/visual-question-answering-on-gli-val>)

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

Data updated: 2026-02-26T06:08:19.301Z

Evaluation of model performance on the validation split of the GLI dataset for visual question answering capabilities, focusing on structural metrics like Volume, Region, Shape, and Spread.

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 Question Answering |
| Dataset (including any stated split) | GLI (val) |
| Metric | Volume Score |
| Unit | SCALAR |
| 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

- [Volume Score](<https://www.sota2.com/research/sota/visual-question-answering-on-gli-val.md?metric=Volume%20Score>): Higher is better; unit: SCALAR.

- [Region Score](<https://www.sota2.com/research/sota/visual-question-answering-on-gli-val.md?metric=Region%20Score>): Higher is better; unit: SCALAR.

- [Shape Score](<https://www.sota2.com/research/sota/visual-question-answering-on-gli-val.md?metric=Shape%20Score>): Higher is better; unit: SCALAR.

- [Spread Score](<https://www.sota2.com/research/sota/visual-question-answering-on-gli-val.md?metric=Spread%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Volume Score | Result date | Report paper |
| --- | --- | --- | --- |
| mpLLM | 43 | Not recorded | 68fa7bc11e209131cea8a379 |
| mpLLM | 43 | Not recorded | 68fa7bc11e209131cea8a379 |
| Both Radiologists | 38 | Not recorded | 68fa7bc11e209131cea8a379 |

### mpLLM

Volume Score: 43. Result ID: 699a4c085698665ec4d38e87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a379.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a379.md>)

Recorded evaluation configuration: {"Agreement between":"Model and Radiologist 1"}. This record does not assert independent reproduction.

### mpLLM

Volume Score: 43. Result ID: 699a4c085698665ec4d38e88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a379.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a379.md>)

Recorded evaluation configuration: {"Agreement between":"Model and Radiologist 2"}. This record does not assert independent reproduction.

### Both Radiologists

Volume Score: 38. Result ID: 699a4c085698665ec4d38e89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a379.md>)

Recorded evaluation configuration: {"Agreement between":"Both Radiologists"}. This record does not assert independent reproduction.

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