# Video Question Answering on EgoSchema (Full/Subset Metrics)

Source: [Video Question Answering on EgoSchema (Full/Subset Metrics)](<https://www.sota2.com/research/sota/video-question-answering-on-egoschema-full-subset-metrics>)

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

Data updated: 2026-03-30T06:39:16.939Z

Evaluation of Video Question Answering performance on the EgoSchema dataset, reporting results categorized under 'Full' and 'Subset' metrics.

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) | EgoSchema |
| Metric | Accuracy (Subset) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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 (Subset)](<https://www.sota2.com/research/sota/video-question-answering-on-egoschema-full-subset-metrics.md?metric=Accuracy%20(Subset)>): Higher is better; unit: PERCENT.

- [Accuracy (Full Set)](<https://www.sota2.com/research/sota/video-question-answering-on-egoschema-full-subset-metrics.md?metric=Accuracy%20(Full%20Set)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Subset) | Result date | Report paper |
| --- | --- | --- | --- |
| A.I.R. | 72.2 | Not recorded | 68fa7be01e209131cea8af78 |
| A.I.R. | 72 | Not recorded | 68fa7be01e209131cea8af78 |
| AKEYS | 68.6 | Not recorded | 68fa7be01e209131cea8af78 |
| T\* | 66.6 | Not recorded | 68fa7be01e209131cea8af78 |
| DrVideo | 66.4 | Not recorded | 68fa7be01e209131cea8af78 |
| A.I.R. | 66.2 | Not recorded | 68fa7be01e209131cea8af78 |
| A.I.R. | 63.2 | Not recorded | 68fa7be01e209131cea8af78 |

### A.I.R.

Accuracy (Subset): 72.2. Result ID: 69ca18fb47f34ce924b20972.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

Recorded evaluation configuration: {"Venue":"-","Base Model":"InternVL3-8B","#Frames":"≤32"}. This record does not assert independent reproduction.

### A.I.R.

Accuracy (Subset): 72. Result ID: 69ca18fb47f34ce924b20970.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

Recorded evaluation configuration: {"Venue":"-","Base Model":"GPT-4o","#Frames":"≤32"}. This record does not assert independent reproduction.

### AKEYS

Accuracy (Subset): 68.6. Result ID: 69ca18fb47f34ce924b2096f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77801e209131cea739ed.md>)

[Implementation](<https://github.com/fansunqi/AKeyS>)

Recorded evaluation configuration: {"Venue":"arXiv’25","Base Model":"GPT-4o","#Frames":"≤32"}. This record does not assert independent reproduction.

### T\*

Accuracy (Subset): 66.6. Result ID: 69ca18fb47f34ce924b2096c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7acd1e209131cea85308.md>)

Recorded evaluation configuration: {"Venue":"CVPR’25","Base Model":"LLaVA-OV-7B","#Frames":"8"}. This record does not assert independent reproduction.

### DrVideo

Accuracy (Subset): 66.4. Result ID: 69ca18fb47f34ce924b2096d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a009.md>)

Recorded evaluation configuration: {"Venue":"CVPR’25","Base Model":"GPT-4","#Frames":"-"}. This record does not assert independent reproduction.

### A.I.R.

Accuracy (Subset): 66.2. Result ID: 69ca18fb47f34ce924b20971.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

Recorded evaluation configuration: {"Venue":"-","Base Model":"Qwen2VL-7B","#Frames":"≤32"}. This record does not assert independent reproduction.

### A.I.R.

Accuracy (Subset): 63.2. Result ID: 69ca18fb47f34ce924b20973.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af78.md>)

Recorded evaluation configuration: {"Venue":"-","Base Model":"LLaVA-OV-7B","#Frames":"≤32"}. This record does not assert independent reproduction.

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