# Video Question Answering on EgoCross (test)

Source: [Video Question Answering on EgoCross (test)](<https://www.sota2.com/research/sota/video-question-answering-on-egocross-test>)

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

Data updated: 2026-05-28T08:13:11.791Z

Evaluation of model performance on the test split of the EgoCross dataset for Video Question Answering, reporting category-specific accuracies and inference cost 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) | EgoCross (test) |
| Metric | Animal 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

- [Animal Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-egocross-test.md?metric=Animal%20Accuracy>): Higher is better; unit: PERCENT.

- [XSports Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-egocross-test.md?metric=XSports%20Accuracy>): Higher is better; unit: PERCENT.

- [Industry Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-egocross-test.md?metric=Industry%20Accuracy>): Higher is better; unit: PERCENT.

- [Surgery Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-egocross-test.md?metric=Surgery%20Accuracy>): Higher is better; unit: PERCENT.

- [Overall Accuracy](<https://www.sota2.com/research/sota/video-question-answering-on-egocross-test.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

- [Input Tokens (M)](<https://www.sota2.com/research/sota/video-question-answering-on-egocross-test.md?metric=Input%20Tokens%20(M)>): Lower is better; unit: SIZE.

- [Cached Tokens (M)](<https://www.sota2.com/research/sota/video-question-answering-on-egocross-test.md?metric=Cached%20Tokens%20(M)>): Lower is better; unit: SIZE.

- [Total Cost ($)](<https://www.sota2.com/research/sota/video-question-answering-on-egocross-test.md?metric=Total%20Cost%20(%24)>): Lower is better; unit: OTHER.

## Recorded results

| Method | Animal Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| RD + timestamps | 79.2 | Not recorded | 6a17cc2ddbd7150506f81419 |
| RD | 71.6 | Not recorded | 6a17cc2ddbd7150506f81419 |
| RD | 71 | Not recorded | 6a17cc2ddbd7150506f81419 |
| zero-shot | 67.8 | Not recorded | 6a17cc2ddbd7150506f81419 |
| zero-shot | 66.7 | Not recorded | 6a17cc2ddbd7150506f81419 |

### RD + timestamps

Animal Accuracy: 79.2. Result ID: 6a17f903fbc373592c119a04.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2ddbd7150506f81419.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc2ddbd7150506f81419.md>)

Recorded evaluation configuration: {"Model":"Gemini 3.1 Pro Preview"}. This record does not assert independent reproduction.

### RD

Animal Accuracy: 71.6. Result ID: 6a17f903fbc373592c119a03.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2ddbd7150506f81419.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc2ddbd7150506f81419.md>)

Recorded evaluation configuration: {"Model":"Gemini 3.1 Pro Preview"}. This record does not assert independent reproduction.

### RD

Animal Accuracy: 71. Result ID: 6a17f903fbc373592c119a06.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2ddbd7150506f81419.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc2ddbd7150506f81419.md>)

Recorded evaluation configuration: {"Model":"Gemini 3.1 Flash Image Preview"}. This record does not assert independent reproduction.

### zero-shot

Animal Accuracy: 67.8. Result ID: 6a17f903fbc373592c119a02.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2ddbd7150506f81419.md>)

Recorded evaluation configuration: {"Model":"Gemini 3.1 Pro Preview"}. This record does not assert independent reproduction.

### zero-shot

Animal Accuracy: 66.7. Result ID: 6a17f903fbc373592c119a05.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2ddbd7150506f81419.md>)

Recorded evaluation configuration: {"Model":"Gemini 3.1 Flash Image Preview"}. This record does not assert independent reproduction.

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