# Open-ended Visual Question Answering on LLS48-VQA

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

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

Data updated: 2026-02-26T05:37:15.431Z

Evaluation of model performance on the LLS48-VQA dataset for open-ended visual question answering, typically measured using generation metrics like BLEU and ROUGE.

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 | Open-ended Visual Question Answering |
| Dataset (including any stated split) | LLS48-VQA |
| Metric | BLEU-1 |
| Unit | SCALAR |
| 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

- [BLEU-1](<https://www.sota2.com/research/sota/open-ended-visual-question-answering-on-lls48-vqa.md?metric=BLEU-1>): Higher is better; unit: SCALAR.

- [BLEU-2](<https://www.sota2.com/research/sota/open-ended-visual-question-answering-on-lls48-vqa.md?metric=BLEU-2>): Higher is better; unit: SCALAR.

- [BLEU-3](<https://www.sota2.com/research/sota/open-ended-visual-question-answering-on-lls48-vqa.md?metric=BLEU-3>): Higher is better; unit: SCALAR.

- [BLEU-4](<https://www.sota2.com/research/sota/open-ended-visual-question-answering-on-lls48-vqa.md?metric=BLEU-4>): Higher is better; unit: SCALAR.

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

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

## Recorded results

| Method | BLEU-1 | Result date | Report paper |
| --- | --- | --- | --- |
| MIS-DINOv2 | 0.5245 | Not recorded | 6993f5e99ebc499c97409912 |
| ZEN | 0.5244 | Not recorded | 6993f5e99ebc499c97409912 |
| SurgeNet | 0.5186 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINOv2 | 0.5175 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINOv2 | 0.5173 | Not recorded | 6993f5e99ebc499c97409912 |
| ZEN | 0.5148 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MAE | 0.5131 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINO | 0.5116 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINOv2 | 0.511 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-DINO | 0.5062 | Not recorded | 6993f5e99ebc499c97409912 |
| SurgeNet | 0.503 | Not recorded | 6993f5e99ebc499c97409912 |
| EndoViT | 0.5009 | Not recorded | 6993f5e99ebc499c97409912 |
| ImageNet | 0.5006 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MoCoV3 | 0.5002 | Not recorded | 6993f5e99ebc499c97409912 |
| PeskaVLP | 0.5 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MoCoV3 | 0.498 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MSN | 0.4926 | Not recorded | 6993f5e99ebc499c97409912 |
| EndoFM | 0.4917 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MAE | 0.4873 | Not recorded | 6993f5e99ebc499c97409912 |
| ImageNet | 0.4846 | Not recorded | 6993f5e99ebc499c97409912 |
| EndoViT | 0.4824 | Not recorded | 6993f5e99ebc499c97409912 |
| EndoFM | 0.482 | Not recorded | 6993f5e99ebc499c97409912 |
| PeskaVLP | 0.4817 | Not recorded | 6993f5e99ebc499c97409912 |
| GSViT | 0.4167 | Not recorded | 6993f5e99ebc499c97409912 |
| MIS-MSN | 0.3992 | Not recorded | 6993f5e99ebc499c97409912 |
| GSViT | 0.3838 | Not recorded | 6993f5e99ebc499c97409912 |

### MIS-DINOv2

BLEU-1: 0.5245. Result ID: 699a78645698665ec401a5fc.

[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","Pre-training Type":"Self-supervised learning","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### ZEN

BLEU-1: 0.5244. Result ID: 699a78645698665ec401a603.

[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","Pre-training Type":"Existing pretrained models","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### SurgeNet

BLEU-1: 0.5186. Result ID: 699a78645698665ec401a602.

[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","Pre-training Type":"Existing pretrained models","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### MIS-DINOv2

BLEU-1: 0.5175. Result ID: 699a78645698665ec401a553.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### MIS-DINOv2

BLEU-1: 0.5173. Result ID: 699a78645698665ec401a5fb.

[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","Pre-training Type":"Self-supervised learning","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### ZEN

BLEU-1: 0.5148. Result ID: 699a78645698665ec401a55a.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### MIS-MAE

BLEU-1: 0.5131. Result ID: 699a78645698665ec401a5f7.

[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","Pre-training Type":"Self-supervised learning","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### MIS-DINO

BLEU-1: 0.5116. Result ID: 699a78645698665ec401a5fa.

[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","Pre-training Type":"Self-supervised learning","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### MIS-DINOv2

BLEU-1: 0.511. Result ID: 699a78645698665ec401a552.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### MIS-DINO

BLEU-1: 0.5062. Result ID: 699a78645698665ec401a551.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### SurgeNet

BLEU-1: 0.503. Result ID: 699a78645698665ec401a559.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### EndoViT

BLEU-1: 0.5009. Result ID: 699a78645698665ec401a600.

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

Recorded evaluation configuration: {"Backbone":"ViT-B","Pre-training Type":"Existing pretrained models","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### ImageNet

BLEU-1: 0.5006. Result ID: 699a78645698665ec401a5fd.

[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","Pre-training Type":"Existing pretrained models","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### MIS-MoCoV3

BLEU-1: 0.5002. Result ID: 699a78645698665ec401a54f.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### PeskaVLP

BLEU-1: 0.5. Result ID: 699a78645698665ec401a601.

[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","Pre-training Type":"Existing pretrained models","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### MIS-MoCoV3

BLEU-1: 0.498. Result ID: 699a78645698665ec401a5f8.

[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","Pre-training Type":"Self-supervised learning","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### MIS-MSN

BLEU-1: 0.4926. Result ID: 699a78645698665ec401a5f9.

[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","Pre-training Type":"Self-supervised learning","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### EndoFM

BLEU-1: 0.4917. Result ID: 699a78645698665ec401a5fe.

[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","Pre-training Type":"Existing pretrained models","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### MIS-MAE

BLEU-1: 0.4873. Result ID: 699a78645698665ec401a54e.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### ImageNet

BLEU-1: 0.4846. Result ID: 699a78645698665ec401a554.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### EndoViT

BLEU-1: 0.4824. Result ID: 699a78645698665ec401a557.

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

Recorded evaluation configuration: {"Backbone":"ViT-B","Backbone status":"frozen"}. This record does not assert independent reproduction.

### EndoFM

BLEU-1: 0.482. Result ID: 699a78645698665ec401a555.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### PeskaVLP

BLEU-1: 0.4817. Result ID: 699a78645698665ec401a558.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### GSViT

BLEU-1: 0.4167. Result ID: 699a78645698665ec401a5ff.

[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","Pre-training Type":"Existing pretrained models","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### MIS-MSN

BLEU-1: 0.3992. Result ID: 699a78645698665ec401a550.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

### GSViT

BLEU-1: 0.3838. Result ID: 699a78645698665ec401a556.

[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","Backbone status":"frozen"}. This record does not assert independent reproduction.

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