# Closed-ended Visual Question Answering on LLS48-VQA

Source: [Closed-ended Visual Question Answering on LLS48-VQA](<https://www.sota2.com/research/sota/closed-ended-visual-question-answering-on-lls48-vqa>)

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

Data updated: 2026-02-26T05:43:43.646Z

Evaluation of model performance on the LLS48-VQA dataset specifically for closed-ended visual question answering tasks, typically measured using classification metrics like F1 score and 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 | Closed-ended Visual Question Answering |
| Dataset (including any stated split) | LLS48-VQA |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 26 of 26 |
| 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/closed-ended-visual-question-answering-on-lls48-vqa.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Balanced Accuracy](<https://www.sota2.com/research/sota/closed-ended-visual-question-answering-on-lls48-vqa.md?metric=Balanced%20Accuracy>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/closed-ended-visual-question-answering-on-lls48-vqa.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| ZEN | 23.35 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINOv2 | 21.74 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINOv2 | 21.3 | Not recorded | 6993f5e99ebc499c97409912 |
| ZEN | 20.76 | Not recorded | 6993f5e99ebc499c97409912 |
| SurgeNet | 20.48 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINOv2 | 20.41 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINO | 19.44 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MAE | 19.34 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINOv2 | 19.23 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINO | 18.83 | Not recorded | 6993f5e99ebc499c97409912 |
| PeskaVLP | 17.64 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MoCoV3 | 17.3 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MoCoV3 | 17.18 | Not recorded | 6993f5e99ebc499c97409912 |
| SurgeNet | 16.46 | Not recorded | 6993f5e99ebc499c97409912 |
| EndoViT | 16.45 | Not recorded | 6993f5e99ebc499c97409912 |
| ImageNet | 15.95 | Not recorded | 6993f5e99ebc499c97409912 |
| PeskaVLP | 15.28 | Not recorded | 6993f5e99ebc499c97409912 |
| ImageNet | 14.83 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MAE | 14.57 | Not recorded | 6993f5e99ebc499c97409912 |
| EndoFM | 14.31 | Not recorded | 6993f5e99ebc499c97409912 |
| EndoFM | 13.75 | Not recorded | 6993f5e99ebc499c97409912 |
| EndoViT | 13.66 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MSN | 12.4 | Not recorded | 6993f5e99ebc499c97409912 |
| GSViT | 5.68 | Not recorded | 6993f5e99ebc499c97409912 |
| GSViT | 5.26 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MSN | 3.99 | Not recorded | 6993f5e99ebc499c97409912 |

### ZEN

F1 Score: 23.35. Result ID: 699a78645698665ec401a5e9.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### MIS-DINOv2

F1 Score: 21.74. Result ID: 699a78645698665ec401a5db.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77041e209131cea70822.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### MIS-DINOv2

F1 Score: 21.3. Result ID: 699a78645698665ec401a5da.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77041e209131cea70822.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### ZEN

F1 Score: 20.76. Result ID: 699a78645698665ec401a5e8.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### SurgeNet

F1 Score: 20.48. Result ID: 699a78645698665ec401a5e7.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76941e209131cea6ddbe.md>)

Recorded evaluation configuration: {"Backbone":"CAFormer18","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### MIS-DINOv2

F1 Score: 20.41. Result ID: 699a78645698665ec401a5d9.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77041e209131cea70822.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### MIS-DINO

F1 Score: 19.44. Result ID: 699a78645698665ec401a5d7.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77041e209131cea70822.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### MIS-MAE

F1 Score: 19.34. Result ID: 699a78645698665ec401a5d1.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7f1e209131cea2e973.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### MIS-DINOv2

F1 Score: 19.23. Result ID: 699a78645698665ec401a5d8.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77041e209131cea70822.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### MIS-DINO

F1 Score: 18.83. Result ID: 699a78645698665ec401a5d6.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77041e209131cea70822.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### PeskaVLP

F1 Score: 17.64. Result ID: 699a78645698665ec401a5e5.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Implementation](<https://github.com/CAMMA-public/SurgVLP>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### MIS-MoCoV3

F1 Score: 17.3. Result ID: 699a78645698665ec401a5d2.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a931e209131cea2903d.md>)

[Implementation](<https://github.com/facebookresearch/moco-v3>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### MIS-MoCoV3

F1 Score: 17.18. Result ID: 699a78645698665ec401a5d3.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a931e209131cea2903d.md>)

[Implementation](<https://github.com/facebookresearch/moco-v3>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### SurgeNet

F1 Score: 16.46. Result ID: 699a78645698665ec401a5e6.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76941e209131cea6ddbe.md>)

Recorded evaluation configuration: {"Backbone":"CAFormer18","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### EndoViT

F1 Score: 16.45. Result ID: 699a78645698665ec401a5e3.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### ImageNet

F1 Score: 15.95. Result ID: 699a78645698665ec401a5dd.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### PeskaVLP

F1 Score: 15.28. Result ID: 699a78645698665ec401a5e4.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77691e209131cea731fe.md>)

[Implementation](<https://github.com/CAMMA-public/SurgVLP>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### ImageNet

F1 Score: 14.83. Result ID: 699a78645698665ec401a5dc.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### MIS-MAE

F1 Score: 14.57. Result ID: 699a78645698665ec401a5d0.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7f1e209131cea2e973.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### EndoFM

F1 Score: 14.31. Result ID: 699a78645698665ec401a5df.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d01e209131cea531b5.md>)

[Implementation](<https://github.com/med-air/Endo-FM>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### EndoFM

F1 Score: 13.75. Result ID: 699a78645698665ec401a5de.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d01e209131cea531b5.md>)

[Implementation](<https://github.com/med-air/Endo-FM>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### EndoViT

F1 Score: 13.66. Result ID: 699a78645698665ec401a5e2.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### MIS-MSN

F1 Score: 12.4. Result ID: 699a78645698665ec401a5d5.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

[Implementation](<https://github.com/facebookresearch/msn>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### GSViT

F1 Score: 5.68. Result ID: 699a78645698665ec401a5e1.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e917f.md>)

Recorded evaluation configuration: {"Backbone":"EfficientViT","Evaluation Protocol":"Fine-tuning backbone"}. This record does not assert independent reproduction.

### GSViT

F1 Score: 5.26. Result ID: 699a78645698665ec401a5e0.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f581e209131ce9e917f.md>)

Recorded evaluation configuration: {"Backbone":"EfficientViT","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

### MIS-MSN

F1 Score: 3.99. Result ID: 699a78645698665ec401a5d4.

[Reporting paper](<https://www.sota2.com/research/paper/6993f5e99ebc499c97409912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

[Implementation](<https://github.com/facebookresearch/msn>)

Recorded evaluation configuration: {"Backbone":"ViT-B","Evaluation Protocol":"Frozen backbone"}. This record does not assert independent reproduction.

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