# Video Question Answering on CG-Bench

Source: [Video Question Answering on CG-Bench](<https://www.sota2.com/research/sota/video-question-answering-on-cg-bench>)

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

Data updated: 2026-04-14T12:24:18.457Z

Evaluation of model performance on the CG-Bench dataset for general Video Question Answering capabilities, typically reporting 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 | Video Question Answering |
| Dataset (including any stated split) | CG-Bench |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/video-question-answering-on-cg-bench.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| POINTS-Long | 37 | Not recorded | 69ddca7d7d0172140ec79f9a |
| POINTS-Long | 36.4 | Not recorded | 69ddca7d7d0172140ec79f9a |
| POINTS-Long | 35.6 | Not recorded | 69ddca7d7d0172140ec79f9a |
| POINTS-Long | 35.5 | Not recorded | 69ddca7d7d0172140ec79f9a |
| POINTS1.5-8B-online | 33.1 | Not recorded | 69ddca7d7d0172140ec79f9a |

### POINTS-Long

Accuracy: 37. Result ID: 69de31e047f34ce924c70326.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7d7d0172140ec79f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca7d7d0172140ec79f9a.md>)

Recorded evaluation configuration: {"Num Frame":"248+8","Token/Frame":"16","Total Num of Token":"5248"}. This record does not assert independent reproduction.

### POINTS-Long

Accuracy: 36.4. Result ID: 69de31e047f34ce924c70324.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7d7d0172140ec79f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca7d7d0172140ec79f9a.md>)

Recorded evaluation configuration: {"Num Frame":"248+8","Token/Frame":"8","Total Num of Token":"3200"}. This record does not assert independent reproduction.

### POINTS-Long

Accuracy: 35.6. Result ID: 69de31e047f34ce924c70327.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7d7d0172140ec79f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca7d7d0172140ec79f9a.md>)

Recorded evaluation configuration: {"Num Frame":"504+8","Token/Frame":"16","Total Num of Token":"9344"}. This record does not assert independent reproduction.

### POINTS-Long

Accuracy: 35.5. Result ID: 69de31e047f34ce924c70325.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7d7d0172140ec79f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca7d7d0172140ec79f9a.md>)

Recorded evaluation configuration: {"Num Frame":"504+8","Token/Frame":"8","Total Num of Token":"5248"}. This record does not assert independent reproduction.

### POINTS1.5-8B-online

Accuracy: 33.1. Result ID: 69de31e047f34ce924c70323.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca7d7d0172140ec79f9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76211e209131cea6b618.md>)

Recorded evaluation configuration: {"Num Frame":"64","Token/Frame":"324","Total Num of Token":"20736"}. This record does not assert independent reproduction.

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