# Average Context Length on NExT-GQA for Video Question Answering

Source: [Average Context Length on NExT-GQA for Video Question Answering](<https://www.sota2.com/research/sota/average-context-length-on-next-gqa-for-video-question-answering>)

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

Data updated: 2026-05-27T08:52:40.645Z

Evaluation focusing on the average context length (in tokens) utilized during single-forward passes for Video Question Answering models on the NExT-GQA dataset.

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) | NExT-GQA |
| Metric | Average Context Length (tokens) |
| Unit | SIZE |
| 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

- [Average Context Length (tokens)](<https://www.sota2.com/research/sota/average-context-length-on-next-gqa-for-video-question-answering.md?metric=Average%20Context%20Length%20(tokens)>): Higher is better; unit: SIZE.

## Recorded results

| Method | Average Context Length (tokens) | Result date | Report paper |
| --- | --- | --- | --- |
| Video-o3 | 55136.3 | Not recorded | 6a167a7fdbd7150506f7ff1a |
| LongVT-RFT | 16389 | Not recorded | 6a167a7fdbd7150506f7ff1a |
| VideoZoomer | 12254.9 | Not recorded | 6a167a7fdbd7150506f7ff1a |
| VideoChat-R1.5-7B | 8897.5 | Not recorded | 6a167a7fdbd7150506f7ff1a |
| LOVE-R1-stage3 | 8480.5 | Not recorded | 6a167a7fdbd7150506f7ff1a |
| DynFrame-8B | 6734.5 | Not recorded | 6a167a7fdbd7150506f7ff1a |
| Video-R1-7B | 3893.2 | Not recorded | 6a167a7fdbd7150506f7ff1a |
| Qwen2.5-VL-7B | 2910.9 | Not recorded | 6a167a7fdbd7150506f7ff1a |

### Video-o3

Average Context Length (tokens): 55136.3. Result ID: 6a16b0ccfbc373592c0ff864.

[Reporting paper](<https://www.sota2.com/research/paper/6a167a7fdbd7150506f7ff1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802fdda8b01e76cc8e185e.md>)

Recorded evaluation configuration: {"Max retrieval / injection":"8"}. This record does not assert independent reproduction.

### LongVT-RFT

Average Context Length (tokens): 16389. Result ID: 6a16b0ccfbc373592c0ff866.

[Reporting paper](<https://www.sota2.com/research/paper/6a167a7fdbd7150506f7ff1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db35d6b0dd3342930e0c.md>)

[Implementation](<https://github.com/EvolvingLMMs-Lab/LongVT>)

Recorded evaluation configuration: {"Max retrieval / injection":"5"}. This record does not assert independent reproduction.

### VideoZoomer

Average Context Length (tokens): 12254.9. Result ID: 6a16b0ccfbc373592c0ff863.

[Reporting paper](<https://www.sota2.com/research/paper/6a167a7fdbd7150506f7ff1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c7e53fdd5c36173d88e.md>)

Recorded evaluation configuration: {"Max retrieval / injection":"4"}. This record does not assert independent reproduction.

### VideoChat-R1.5-7B

Average Context Length (tokens): 8897.5. Result ID: 6a16b0ccfbc373592c0ff865.

[Reporting paper](<https://www.sota2.com/research/paper/6a167a7fdbd7150506f7ff1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b8f1e209131cea891be.md>)

Recorded evaluation configuration: {"Max retrieval / injection":"2"}. This record does not assert independent reproduction.

### LOVE-R1-stage3

Average Context Length (tokens): 8480.5. Result ID: 6a16b0ccfbc373592c0ff867.

[Reporting paper](<https://www.sota2.com/research/paper/6a167a7fdbd7150506f7ff1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bae1e209131cea89d48.md>)

Recorded evaluation configuration: {"Max retrieval / injection":"2"}. This record does not assert independent reproduction.

### DynFrame-8B

Average Context Length (tokens): 6734.5. Result ID: 6a16b0ccfbc373592c0ff868.

[Reporting paper](<https://www.sota2.com/research/paper/6a167a7fdbd7150506f7ff1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167a7fdbd7150506f7ff1a.md>)

Recorded evaluation configuration: {"Max retrieval / injection":"1"}. This record does not assert independent reproduction.

### Video-R1-7B

Average Context Length (tokens): 3893.2. Result ID: 6a16b0ccfbc373592c0ff862.

[Reporting paper](<https://www.sota2.com/research/paper/6a167a7fdbd7150506f7ff1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c6f1e209131cea8e0ec.md>)

Recorded evaluation configuration: {"Max retrieval / injection":"0"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Average Context Length (tokens): 2910.9. Result ID: 6a16b0ccfbc373592c0ff861.

[Reporting paper](<https://www.sota2.com/research/paper/6a167a7fdbd7150506f7ff1a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Max retrieval / injection":"0"}. This record does not assert independent reproduction.

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