# Video Physical Commonsense Evaluation on VideoPhy-2

Source: [Video Physical Commonsense Evaluation on VideoPhy-2](<https://www.sota2.com/research/sota/video-physical-commonsense-evaluation-on-videophy-2>)

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

Data updated: 2026-02-26T06:04:37.038Z

Evaluation of model performance on the VideoPhy-2 dataset for Video Physical Commonsense Evaluation, reporting Spearman (PC) 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 Physical Commonsense Evaluation |
| Dataset (including any stated split) | VideoPhy-2 |
| Metric | Spearman PC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Spearman PC](<https://www.sota2.com/research/sota/video-physical-commonsense-evaluation-on-videophy-2.md?metric=Spearman%20PC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Spearman PC | Result date | Report paper |
| --- | --- | --- | --- |
| VIDEOPHY–2–AUTOEVAL | 0.76 | Not recorded | 699e820c6017c4460ffacf16 |
| 3DSPA (ours) | 0.74 | Not recorded | 699e820c6017c4460ffacf16 |
| 3DSPA (no DINO) | 0.5 | Not recorded | 699e820c6017c4460ffacf16 |
| VideoCon–Physics | 0.48 | Not recorded | 699e820c6017c4460ffacf16 |
| 3DSPA (no 3D) | 0.4 | Not recorded | 699e820c6017c4460ffacf16 |
| 3DSPA (no 3D, no DINO) | 0.19 | Not recorded | 699e820c6017c4460ffacf16 |
| VideoScore | 0.17 | Not recorded | 699e820c6017c4460ffacf16 |
| VideoCon | 0.13 | Not recorded | 699e820c6017c4460ffacf16 |
| VideoLlava | 0.08 | Not recorded | 699e820c6017c4460ffacf16 |

### VIDEOPHY–2–AUTOEVAL

Spearman PC: 0.76. Result ID: 699eab0a5698665ec477741a.

[Reporting paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77551e209131cea72737.md>)

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

### 3DSPA (ours)

Spearman PC: 0.74. Result ID: 699eab0a5698665ec477741e.

[Reporting paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

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

### 3DSPA (no DINO)

Spearman PC: 0.5. Result ID: 699eab0a5698665ec477741d.

[Reporting paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

Recorded evaluation configuration: {"fine-tuned":false,"DINO features":false}. This record does not assert independent reproduction.

### VideoCon–Physics

Spearman PC: 0.48. Result ID: 699eab0a5698665ec4777416.

[Reporting paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77481e209131cea723d2.md>)

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

### 3DSPA (no 3D)

Spearman PC: 0.4. Result ID: 699eab0a5698665ec477741c.

[Reporting paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

Recorded evaluation configuration: {"fine-tuned":false,"3D structure":false}. This record does not assert independent reproduction.

### 3DSPA (no 3D, no DINO)

Spearman PC: 0.19. Result ID: 699eab0a5698665ec477741b.

[Reporting paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

Recorded evaluation configuration: {"fine-tuned":false,"3D structure":false,"DINO features":false}. This record does not assert independent reproduction.

### VideoScore

Spearman PC: 0.17. Result ID: 699eab0a5698665ec4777419.

[Reporting paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

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

### VideoCon

Spearman PC: 0.13. Result ID: 699eab0a5698665ec4777417.

[Reporting paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77481e209131cea723d2.md>)

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

### VideoLlava

Spearman PC: 0.08. Result ID: 699eab0a5698665ec4777418.

[Reporting paper](<https://www.sota2.com/research/paper/699e820c6017c4460ffacf16.md>)

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

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