# Open-Ended VideoQA on ANet-QA

Source: [Open-Ended VideoQA on ANet-QA](<https://www.sota2.com/research/sota/open-ended-videoqa-on-anet-qa>)

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

Data updated: 2026-02-26T05:30:08.314Z

Evaluation of model performance on the ANet-QA dataset for Open-Ended Video Question Answering tasks, reporting Accuracy and Score.

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 VideoQA |
| Dataset (including any stated split) | ANet-QA |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 34 of 34 |
| 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/open-ended-videoqa-on-anet-qa.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Score](<https://www.sota2.com/research/sota/open-ended-videoqa-on-anet-qa.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LLaVA-NeXT-Video-DPO | 64.4 | Not recorded | 68fa74c91e209131cea63cb0 |
| LLaVA-NeXT-Video-DPO | 64.4 | Not recorded | 68fa75c51e209131cea69da9 |
| PLLaVA | 60.9 | Not recorded | 68fa74c91e209131cea63cb0 |
| PLLAVA | 60.9 | Not recorded | 68fa75c51e209131cea69da9 |
| LLaVA-NeXT-Video-DPO | 60.2 | Not recorded | 68fa75c51e209131cea69da9 |
| SF-LLaVA-34B | 59.2 | Not recorded | 68fa74c91e209131cea63cb0 |
| SF-LLAVA | 59.2 | Not recorded | 68fa75c51e209131cea69da9 |
| TS-LLAVA | 58.9 | Not recorded | 68fa75c51e209131cea69da9 |
| LLaVA-NeXT-Video | 58.8 | Not recorded | 68fa74c91e209131cea63cb0 |
| LLaVA-NeXT-Video | 58.8 | Not recorded | 68fa75c51e209131cea69da9 |
| IG-VLM (LLaVA-v1.6) | 58.4 | Not recorded | 68fa74c91e209131cea63cb0 |
| IG-VLM | 58.4 | Not recorded | 68fa75c51e209131cea69da9 |
| TS-LLaVA | 56.7 | Not recorded | 68fa75c51e209131cea69da9 |
| PLLAVA | 56.3 | Not recorded | 68fa75c51e209131cea69da9 |
| LLaVA-NeXT-Image | 55.6 | Not recorded | 68fa74c91e209131cea63cb0 |
| LLaVA-NeXT-Image | 55.6 | Not recorded | 68fa75c51e209131cea69da9 |
| SF-LLaVA | 55.5 | Not recorded | 68fa75c51e209131cea69da9 |
| IG-VLM | 54.3 | Not recorded | 68fa75c51e209131cea69da9 |
| LLaVA-NeXT-Image | 53.8 | Not recorded | 68fa75c51e209131cea69da9 |
| LLaVA-NeXT-Video | 53.5 | Not recorded | 68fa75c51e209131cea69da9 |
| FreeVA | 51.2 | Not recorded | 68fa75c51e209131cea69da9 |
| VideoGPT+ | 50.6 | Not recorded | 68fa75c51e209131cea69da9 |
| Video-LLaMA2 | 50.3 | Not recorded | 68fa74c91e209131cea63cb0 |
| Video-LLaMA2 | 50.2 | Not recorded | 68fa75c51e209131cea69da9 |
| DeepStack-L | 49.3 | Not recorded | 68fa75c51e209131cea69da9 |
| VideoChat2 | 49.1 | Not recorded | 68fa75c51e209131cea69da9 |
| Vista-LLaMA | 48.3 | Not recorded | 68fa75c51e209131cea69da9 |
| MovieChat+ | 48.1 | Not recorded | 68fa75c51e209131cea69da9 |
| LLaMA-VID | 47.4 | Not recorded | 68fa75c51e209131cea69da9 |
| MovieChat | 45.7 | Not recorded | 68fa75c51e209131cea69da9 |
| Video-LLaVA | 45.3 | Not recorded | 68fa75c51e209131cea69da9 |
| Video-ChatGPT | 35.2 | Not recorded | 68fa75c51e209131cea69da9 |
| VideoChat | 26.5 | Not recorded | 68fa75c51e209131cea69da9 |
| Video-LLaMA | 12.4 | Not recorded | 68fa75c51e209131cea69da9 |

### LLaVA-NeXT-Video-DPO

Accuracy: 64.4. Result ID: 69937b953a6c314849164332.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L"}. This record does not assert independent reproduction.

### LLaVA-NeXT-Video-DPO

Accuracy: 64.4. Result ID: 6993e5953a6c314849194682.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L","Training-free":false}. This record does not assert independent reproduction.

### PLLaVA

Accuracy: 60.9. Result ID: 69937b953a6c314849164330.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a3ea.md>)

[Implementation](<https://pllava.github.io/>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L"}. This record does not assert independent reproduction.

### PLLAVA

Accuracy: 60.9. Result ID: 6993e5953a6c314849194680.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a3ea.md>)

[Implementation](<https://pllava.github.io/>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L","Training-free":false}. This record does not assert independent reproduction.

### LLaVA-NeXT-Video-DPO

Accuracy: 60.2. Result ID: 6993e5953a6c314849194679.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":false}. This record does not assert independent reproduction.

### SF-LLaVA-34B

Accuracy: 59.2. Result ID: 69937b953a6c314849164335.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

[Implementation](<https://huggingface.co/collections/liuhaotian/llava-next-65b9e40155f60fd046a5ccf2>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L"}. This record does not assert independent reproduction.

### SF-LLAVA

Accuracy: 59.2. Result ID: 6993e5953a6c314849194685.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

[Implementation](<https://huggingface.co/collections/liuhaotian/llava-next-65b9e40155f60fd046a5ccf2>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L","Training-free":true}. This record does not assert independent reproduction.

### TS-LLAVA

Accuracy: 58.9. Result ID: 6993e5953a6c314849194686.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Implementation](<https://github.com/tingyu215/TS-LLaVA>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L","Training-free":true}. This record does not assert independent reproduction.

### LLaVA-NeXT-Video

Accuracy: 58.8. Result ID: 69937b953a6c314849164331.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L"}. This record does not assert independent reproduction.

### LLaVA-NeXT-Video

Accuracy: 58.8. Result ID: 6993e5953a6c314849194681.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L","Training-free":false}. This record does not assert independent reproduction.

### IG-VLM (LLaVA-v1.6)

Accuracy: 58.4. Result ID: 69937b953a6c314849164334.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581e0.md>)

[Implementation](<https://github.com/imagegridworth/IG-VLM>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L"}. This record does not assert independent reproduction.

### IG-VLM

Accuracy: 58.4. Result ID: 6993e5953a6c314849194684.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581e0.md>)

[Implementation](<https://github.com/imagegridworth/IG-VLM>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L","Training-free":true}. This record does not assert independent reproduction.

### TS-LLaVA

Accuracy: 56.7. Result ID: 6993e5953a6c31484919467f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Implementation](<https://github.com/tingyu215/TS-LLaVA>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":true}. This record does not assert independent reproduction.

### PLLAVA

Accuracy: 56.3. Result ID: 6993e5953a6c314849194677.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a3ea.md>)

[Implementation](<https://pllava.github.io/>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":false}. This record does not assert independent reproduction.

### LLaVA-NeXT-Image

Accuracy: 55.6. Result ID: 69937b953a6c314849164333.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L"}. This record does not assert independent reproduction.

### LLaVA-NeXT-Image

Accuracy: 55.6. Result ID: 6993e5953a6c314849194683.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

Recorded evaluation configuration: {"LLM Size":"34B","Vision Encoder":"CLIP-L","Training-free":true}. This record does not assert independent reproduction.

### SF-LLaVA

Accuracy: 55.5. Result ID: 6993e5953a6c31484919467e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

[Implementation](<https://huggingface.co/collections/liuhaotian/llava-next-65b9e40155f60fd046a5ccf2>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":true}. This record does not assert independent reproduction.

### IG-VLM

Accuracy: 54.3. Result ID: 6993e5953a6c31484919467d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581e0.md>)

[Implementation](<https://github.com/imagegridworth/IG-VLM>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":true}. This record does not assert independent reproduction.

### LLaVA-NeXT-Image

Accuracy: 53.8. Result ID: 6993e5953a6c31484919467c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":true}. This record does not assert independent reproduction.

### LLaVA-NeXT-Video

Accuracy: 53.5. Result ID: 6993e5953a6c314849194678.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":false}. This record does not assert independent reproduction.

### FreeVA

Accuracy: 51.2. Result ID: 6993e5953a6c31484919467a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73861e209131cea5cf32.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":true}. This record does not assert independent reproduction.

### VideoGPT+

Accuracy: 50.6. Result ID: 6993e5953a6c31484919466f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73841e209131cea5ce32.md>)

[Implementation](<https://github.com/mbzuai-oryx/Video-ChatGPT>)

Recorded evaluation configuration: {"LLM Size":"3.8B","Vision Encoder":"CLIP-L","Training-free":false}. This record does not assert independent reproduction.

### Video-LLaMA2

Accuracy: 50.3. Result ID: 69937b953a6c31484916432f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c91e209131cea63cb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75761e209131cea681dd.md>)

[Implementation](<https://github.com/DAMO-NLP-SG/VideoLLaMA2>)

Recorded evaluation configuration: {"LLM Size":"46.7B","Vision Encoder":"CLIP-L"}. This record does not assert independent reproduction.

### Video-LLaMA2

Accuracy: 50.2. Result ID: 6993e5953a6c31484919466d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75761e209131cea681dd.md>)

[Implementation](<https://github.com/DAMO-NLP-SG/VideoLLaMA2>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":false}. This record does not assert independent reproduction.

### DeepStack-L

Accuracy: 49.3. Result ID: 6993e5953a6c31484919467b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738e1e209131cea5d313.md>)

[Implementation](<https://deepstack-vl.github.io/>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":true}. This record does not assert independent reproduction.

### VideoChat2

Accuracy: 49.1. Result ID: 6993e5953a6c314849194674.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73411e209131cea5b4b7.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"UMT-L","Training-free":false}. This record does not assert independent reproduction.

### Vista-LLaMA

Accuracy: 48.3. Result ID: 6993e5953a6c314849194675.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71cee.md>)

[Implementation](<https://jinxxian.github.io/Vista-LLaMA>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-G","Training-free":false}. This record does not assert independent reproduction.

### MovieChat+

Accuracy: 48.1. Result ID: 6993e5953a6c314849194672.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa730d1e209131cea5a274.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-G","Training-free":false}. This record does not assert independent reproduction.

### LLaMA-VID

Accuracy: 47.4. Result ID: 6993e5953a6c314849194676.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea50559.md>)

[Implementation](<https://github.com/dvlab-research/LLaMA-VID>)

Recorded evaluation configuration: {"LLM Size":"13B","Vision Encoder":"CLIP-G","Training-free":false}. This record does not assert independent reproduction.

### MovieChat

Accuracy: 45.7. Result ID: 6993e5953a6c314849194671.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56563.md>)

[Implementation](<https://rese1f.github.io/MovieChat>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-G","Training-free":false}. This record does not assert independent reproduction.

### Video-LLaVA

Accuracy: 45.3. Result ID: 6993e5953a6c314849194670.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75051e209131cea65534.md>)

[Implementation](<https://github.com/PKU-YuanGroup/Video-LLaVA>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"ViT-L","Training-free":false}. This record does not assert independent reproduction.

### Video-ChatGPT

Accuracy: 35.2. Result ID: 6993e5953a6c31484919466e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73841e209131cea5ce32.md>)

[Implementation](<https://github.com/mbzuai-oryx/Video-ChatGPT>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-L","Training-free":false}. This record does not assert independent reproduction.

### VideoChat

Accuracy: 26.5. Result ID: 6993e5953a6c314849194673.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ba1e209131cea52cc7.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-G","Training-free":false}. This record does not assert independent reproduction.

### Video-LLaMA

Accuracy: 12.4. Result ID: 6993e5953a6c31484919466c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75c51e209131cea69da9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e393.md>)

[Implementation](<https://github.com/DAMO-NLP-SG/Video-LLaMA>)

Recorded evaluation configuration: {"LLM Size":"7B","Vision Encoder":"CLIP-G","Training-free":false}. This record does not assert independent reproduction.

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