# Audio-Visual Question Answering on Daily-Omni 1 FPS

Source: [Audio-Visual Question Answering on Daily-Omni 1 FPS](<https://www.sota2.com/research/sota/audio-visual-question-answering-on-daily-omni-1-fps>)

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

Data updated: 2026-05-26T11:49:24.220Z

Evaluation of model performance on the Daily-Omni dataset sampled at 1 Frame Per Second (1 FPS) for Audio-Visual Question Answering tasks, utilizing specific metrics like AVA, CP, CU, ES, IF, RS, 30, and 60.

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 | Audio-Visual Question Answering |
| Dataset (including any stated split) | Daily-Omni 1 FPS |
| Metric | Metric 30 |
| 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

- [Metric 30](<https://www.sota2.com/research/sota/audio-visual-question-answering-on-daily-omni-1-fps.md?metric=Metric%2030>): Higher is better; unit: PERCENT.

- [Metric 60](<https://www.sota2.com/research/sota/audio-visual-question-answering-on-daily-omni-1-fps.md?metric=Metric%2060>): Higher is better; unit: PERCENT.

- [AVA Score](<https://www.sota2.com/research/sota/audio-visual-question-answering-on-daily-omni-1-fps.md?metric=AVA%20Score>): Higher is better; unit: PERCENT.

- [CP Score](<https://www.sota2.com/research/sota/audio-visual-question-answering-on-daily-omni-1-fps.md?metric=CP%20Score>): Higher is better; unit: PERCENT.

- [CU Score](<https://www.sota2.com/research/sota/audio-visual-question-answering-on-daily-omni-1-fps.md?metric=CU%20Score>): Higher is better; unit: PERCENT.

- [ES Score](<https://www.sota2.com/research/sota/audio-visual-question-answering-on-daily-omni-1-fps.md?metric=ES%20Score>): Higher is better; unit: PERCENT.

- [IF Score](<https://www.sota2.com/research/sota/audio-visual-question-answering-on-daily-omni-1-fps.md?metric=IF%20Score>): Higher is better; unit: PERCENT.

- [RS Score](<https://www.sota2.com/research/sota/audio-visual-question-answering-on-daily-omni-1-fps.md?metric=RS%20Score>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/audio-visual-question-answering-on-daily-omni-1-fps.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Metric 30 | Result date | Report paper |
| --- | --- | --- | --- |
| StreamOV | 70.9 | Not recorded | 6a152948dbd7150506f7e181 |
| Qwen3-Omni-30B | 70 | Not recorded | 6a152948dbd7150506f7e181 |
| Gemini 2.5 Flash | 69.9 | Not recorded | 6a152948dbd7150506f7e181 |
| Gemini 2.0 Flash | 67.2 | Not recorded | 6a152948dbd7150506f7e181 |
| Qwen3-VL-30B | 57.3 | Not recorded | 6a152948dbd7150506f7e181 |
| GPT-4o | 55.6 | Not recorded | 6a152948dbd7150506f7e181 |
| Qwen2.5-Omni-7B | 48.7 | Not recorded | 6a152948dbd7150506f7e181 |
| Qwen2.5-VL-7B | 39.3 | Not recorded | 6a152948dbd7150506f7e181 |

### StreamOV

Metric 30: 70.9. Result ID: 6a15889bfbc373592c0e0d56.

[Reporting paper](<https://www.sota2.com/research/paper/6a152948dbd7150506f7e181.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a152948dbd7150506f7e181.md>)

Recorded evaluation configuration: {"Audio":"true"}. This record does not assert independent reproduction.

### Qwen3-Omni-30B

Metric 30: 70. Result ID: 6a15889bfbc373592c0e0d55.

[Reporting paper](<https://www.sota2.com/research/paper/6a152948dbd7150506f7e181.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b881e209131cea88f3d.md>)

Recorded evaluation configuration: {"Audio":"true"}. This record does not assert independent reproduction.

### Gemini 2.5 Flash

Metric 30: 69.9. Result ID: 6a15889bfbc373592c0e0d50.

[Reporting paper](<https://www.sota2.com/research/paper/6a152948dbd7150506f7e181.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

Recorded evaluation configuration: {"Audio":"true"}. This record does not assert independent reproduction.

### Gemini 2.0 Flash

Metric 30: 67.2. Result ID: 6a15889bfbc373592c0e0d4f.

[Reporting paper](<https://www.sota2.com/research/paper/6a152948dbd7150506f7e181.md>)

Recorded evaluation configuration: {"Audio":"true"}. This record does not assert independent reproduction.

### Qwen3-VL-30B

Metric 30: 57.3. Result ID: 6a15889bfbc373592c0e0d54.

[Reporting paper](<https://www.sota2.com/research/paper/6a152948dbd7150506f7e181.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Audio":"false"}. This record does not assert independent reproduction.

### GPT-4o

Metric 30: 55.6. Result ID: 6a15889bfbc373592c0e0d51.

[Reporting paper](<https://www.sota2.com/research/paper/6a152948dbd7150506f7e181.md>)

Recorded evaluation configuration: {"Audio":"false"}. This record does not assert independent reproduction.

### Qwen2.5-Omni-7B

Metric 30: 48.7. Result ID: 6a15889bfbc373592c0e0d53.

[Reporting paper](<https://www.sota2.com/research/paper/6a152948dbd7150506f7e181.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea7482c.md>)

Recorded evaluation configuration: {"Audio":"true"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Metric 30: 39.3. Result ID: 6a15889bfbc373592c0e0d52.

[Reporting paper](<https://www.sota2.com/research/paper/6a152948dbd7150506f7e181.md>)

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

Recorded evaluation configuration: {"Audio":"false"}. This record does not assert independent reproduction.

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