# Physical Audiovisual CommonSense Reasoning on PACS-Material (test)

Source: [Physical Audiovisual CommonSense Reasoning on PACS-Material (test)](<https://www.sota2.com/research/sota/physical-audiovisual-commonsense-reasoning-on-pacs-material-test>)

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

Data updated: 2026-02-26T05:29:17.865Z

Evaluation of model performance on the test split of the PACS-Material dataset for Physical Audiovisual CommonSense Reasoning tasks, measured by Accuracy.

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 | Physical Audiovisual CommonSense Reasoning |
| Dataset (including any stated split) | PACS-Material (test) |
| Metric | Accuracy |
| 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](<https://www.sota2.com/research/sota/physical-audiovisual-commonsense-reasoning-on-pacs-material-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| AudioCLIP w/ DCL | 76.2 | Not recorded | 68fa71141e209131cea4f214 |
| AudioCLIP | 75.9 | Not recorded | 68fa71141e209131cea4f214 |
| UNITER w/ DCL\* | 75.7 | Not recorded | 68fa71141e209131cea4f214 |
| CLIP w/ DCL | 75.4 | Not recorded | 68fa71141e209131cea4f214 |
| UNITER(Large) | 75 | Not recorded | 68fa71141e209131cea4f214 |
| CLIP | 72.4 | Not recorded | 68fa71141e209131cea4f214 |
| Late Fusion w/ DCL | 69.7 | Not recorded | 68fa71141e209131cea4f214 |
| Late Fusion | 67.4 | Not recorded | 68fa71141e209131cea4f214 |

### AudioCLIP w/ DCL

Accuracy: 76.2. Result ID: 6991b0bb3a6c31484909ee59.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Implementation](<https://github.com/Andy20178/DCL>)

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

### AudioCLIP

Accuracy: 75.9. Result ID: 6991b0bb3a6c31484909ee58.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d6a1e209131cea39b2c.md>)

[Implementation](<https://github.com/AndreyGuzhov/AudioCLIP>)

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

### UNITER w/ DCL\*

Accuracy: 75.7. Result ID: 6991b0bb3a6c31484909ee5b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Implementation](<https://github.com/Andy20178/DCL>)

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

### CLIP w/ DCL

Accuracy: 75.4. Result ID: 6991b0bb3a6c31484909ee57.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Implementation](<https://github.com/Andy20178/DCL>)

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

### UNITER(Large)

Accuracy: 75. Result ID: 6991b0bb3a6c31484909ee5a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67f91e209131cea1989f.md>)

[Implementation](<https://github.com/ChenRocks/UNITER>)

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

### CLIP

Accuracy: 72.4. Result ID: 6991b0bb3a6c31484909ee56.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

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

### Late Fusion w/ DCL

Accuracy: 69.7. Result ID: 6991b0bb3a6c31484909ee55.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

[Implementation](<https://github.com/Andy20178/DCL>)

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

### Late Fusion

Accuracy: 67.4. Result ID: 6991b0bb3a6c31484909ee54.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f214.md>)

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

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