# Audio-video understanding on AV-Counting

Source: [Audio-video understanding on AV-Counting](<https://www.sota2.com/research/sota/audio-video-understanding-on-av-counting>)

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

Data updated: 2026-03-31T09:10:41.584Z

Evaluation of Audio-video understanding performance on the AV-Counting dataset, reporting the primary score metric.

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-video understanding |
| Dataset (including any stated split) | AV-Counting |
| Metric | Primary Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Primary Score](<https://www.sota2.com/research/sota/audio-video-understanding-on-av-counting.md?metric=Primary%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Primary Score | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen2.5-Omni + AVATAR | 23.1 | Not recorded | 68fa7a631e209131cea82cee |
| AV-Reasoner | 23 | Not recorded | 68fa7a631e209131cea82cee |
| Qwen2.5-Omni + GRPO | 22.8 | Not recorded | 68fa7a631e209131cea82cee |
| Echolnk | 22.7 | Not recorded | 68fa7a631e209131cea82cee |
| Qwen2.5-Omni | 22.3 | Not recorded | 68fa7a631e209131cea82cee |
| Omni-R1 | 22 | Not recorded | 68fa7a631e209131cea82cee |
| HumanOmni | 19.6 | Not recorded | 68fa7a631e209131cea82cee |
| Ola-7B + AVATAR | 19.5 | Not recorded | 68fa7a631e209131cea82cee |
| Ola-7B + GRPO | 18.2 | Not recorded | 68fa7a631e209131cea82cee |
| Ola-7B | 17.4 | Not recorded | 68fa7a631e209131cea82cee |

### Qwen2.5-Omni + AVATAR

Primary Score: 23.1. Result ID: 69cb8eb247f34ce924b411b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

Recorded evaluation configuration: {"Reinforcement Learning Strategy":"AVATAR"}. This record does not assert independent reproduction.

### AV-Reasoner

Primary Score: 23. Result ID: 69cb8eb247f34ce924b411ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81903.md>)

Recorded evaluation configuration: {"Reinforcement Learning Strategy":"N/A"}. This record does not assert independent reproduction.

### Qwen2.5-Omni + GRPO

Primary Score: 22.8. Result ID: 69cb8eb247f34ce924b411b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

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

Recorded evaluation configuration: {"Reinforcement Learning Strategy":"GRPO"}. This record does not assert independent reproduction.

### Echolnk

Primary Score: 22.7. Result ID: 69cb8eb247f34ce924b411a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79811e209131cea7ddb0.md>)

Recorded evaluation configuration: {"Reinforcement Learning Strategy":"N/A"}. This record does not assert independent reproduction.

### Qwen2.5-Omni

Primary Score: 22.3. Result ID: 69cb8eb247f34ce924b411b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

Recorded evaluation configuration: {"Reinforcement Learning Strategy":"Baseline"}. This record does not assert independent reproduction.

### Omni-R1

Primary Score: 22. Result ID: 69cb8eb247f34ce924b411aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78da1e209131cea7acde.md>)

Recorded evaluation configuration: {"Reinforcement Learning Strategy":"N/A"}. This record does not assert independent reproduction.

### HumanOmni

Primary Score: 19.6. Result ID: 69cb8eb247f34ce924b411ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecef.md>)

Recorded evaluation configuration: {"Reinforcement Learning Strategy":"N/A"}. This record does not assert independent reproduction.

### Ola-7B + AVATAR

Primary Score: 19.5. Result ID: 69cb8eb247f34ce924b411af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

Recorded evaluation configuration: {"Reinforcement Learning Strategy":"AVATAR"}. This record does not assert independent reproduction.

### Ola-7B + GRPO

Primary Score: 18.2. Result ID: 69cb8eb247f34ce924b411ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7c004.md>)

Recorded evaluation configuration: {"Reinforcement Learning Strategy":"GRPO"}. This record does not assert independent reproduction.

### Ola-7B

Primary Score: 17.4. Result ID: 69cb8eb247f34ce924b411ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a631e209131cea82cee.md>)

Recorded evaluation configuration: {"Reinforcement Learning Strategy":"Baseline"}. This record does not assert independent reproduction.

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