# Visual Question Answering on SLAKE Closed

Source: [Visual Question Answering on SLAKE Closed](<https://www.sota2.com/research/sota/visual-question-answering-on-slake-closed>)

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

Data updated: 2026-04-21T08:56:38.427Z

Evaluation of Visual Question Answering performance on the closed subset of the SLAKE dataset, focusing on token-level recall and F1 scores.

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) | SLAKE Closed |
| Metric | Token Recall |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Token Recall](<https://www.sota2.com/research/sota/visual-question-answering-on-slake-closed.md?metric=Token%20Recall>): Higher is better; unit: PERCENT.

- [Token F1](<https://www.sota2.com/research/sota/visual-question-answering-on-slake-closed.md?metric=Token%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Token Recall | Result date | Report paper |
| --- | --- | --- | --- |
| BiomedGPT-B | 90 | Not recorded | 68fa7c0f1e209131cea8c31b |
| CLARE | 90 | Not recorded | 68fa7c0f1e209131cea8c31b |
| CLARE | 90 | Not recorded | 68fa7c0f1e209131cea8c31b |
| MMed-RAG | 89 | Not recorded | 68fa7c0f1e209131cea8c31b |
| LLaVA-Med | 87 | Not recorded | 68fa7c0f1e209131cea8c31b |
| LLaVA-Med | 85 | Not recorded | 68fa7c0f1e209131cea8c31b |
| LLaVA-Med | 83 | Not recorded | 68fa7c0f1e209131cea8c31b |

### BiomedGPT-B

Token Recall: 90. Result ID: 69e73bbc47f34ce924cd9925.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0f1e209131cea8c31b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70591e209131cea4a74b.md>)

[Implementation](<https://github.com/PharMolix/OpenBioMed>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CLARE

Token Recall: 90. Result ID: 69e73bbc47f34ce924cd9929.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0f1e209131cea8c31b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c0f1e209131cea8c31b.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2-vl"}. This record does not assert independent reproduction.

### CLARE

Token Recall: 90. Result ID: 69e73bbc47f34ce924cd992a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0f1e209131cea8c31b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c0f1e209131cea8c31b.md>)

Recorded evaluation configuration: {"Backbone":"Pixtral"}. This record does not assert independent reproduction.

### MMed-RAG

Token Recall: 89. Result ID: 69e73bbc47f34ce924cd9924.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0f1e209131cea8c31b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773f1e209131cea71f9a.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-Med"}. This record does not assert independent reproduction.

### LLaVA-Med

Token Recall: 87. Result ID: 69e73bbc47f34ce924cd9928.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0f1e209131cea8c31b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f8e1e209131cea46356.md>)

[Implementation](<https://aka.ms/llava-med>)

Recorded evaluation configuration: {"Backbone":"BioMedCLIP"}. This record does not assert independent reproduction.

### LLaVA-Med

Token Recall: 85. Result ID: 69e73bbc47f34ce924cd9927.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0f1e209131cea8c31b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f8e1e209131cea46356.md>)

[Implementation](<https://aka.ms/llava-med>)

Recorded evaluation configuration: {"Backbone":"Vicuna"}. This record does not assert independent reproduction.

### LLaVA-Med

Token Recall: 83. Result ID: 69e73bbc47f34ce924cd9926.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0f1e209131cea8c31b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f8e1e209131cea46356.md>)

[Implementation](<https://aka.ms/llava-med>)

Recorded evaluation configuration: {"Backbone":"LLaVA"}. This record does not assert independent reproduction.

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