# Video Understanding on VidHalluc

Source: [Video Understanding on VidHalluc](<https://www.sota2.com/research/sota/video-understanding-on-vidhalluc>)

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

Data updated: 2026-04-06T08:48:47.351Z

Evaluation of general Video Understanding performance on the VidHalluc dataset, typically 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 | Video Understanding |
| Dataset (including any stated split) | VidHalluc |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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/video-understanding-on-vidhalluc.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| STEAR | 83.84 | Not recorded | 69d33def7d0172140ec735ff |
| VCD | 83.19 | Not recorded | 69d33def7d0172140ec735ff |
| DINO-HEAL | 82.95 | Not recorded | 69d33def7d0172140ec735ff |
| TCD | 82.67 | Not recorded | 69d33def7d0172140ec735ff |
| MemVR | 81.87 | Not recorded | 69d33def7d0172140ec735ff |
| Baseline | 81.7 | Not recorded | 69d33def7d0172140ec735ff |
| STEAR | 73.19 | Not recorded | 69d33def7d0172140ec735ff |
| TCD | 71.51 | Not recorded | 69d33def7d0172140ec735ff |
| DINO-HEAL | 71.09 | Not recorded | 69d33def7d0172140ec735ff |
| MemVR | 70.69 | Not recorded | 69d33def7d0172140ec735ff |
| Baseline | 70.2 | Not recorded | 69d33def7d0172140ec735ff |
| VCD | 68.47 | Not recorded | 69d33def7d0172140ec735ff |
| STEAR | 65.81 | Not recorded | 69d33def7d0172140ec735ff |
| MemVR | 65.69 | Not recorded | 69d33def7d0172140ec735ff |
| DINO-HEAL | 65.58 | Not recorded | 69d33def7d0172140ec735ff |
| VCD | 65.48 | Not recorded | 69d33def7d0172140ec735ff |
| TCD | 64.39 | Not recorded | 69d33def7d0172140ec735ff |
| Baseline | 63.07 | Not recorded | 69d33def7d0172140ec735ff |

### STEAR

Accuracy: 83.84. Result ID: 69d3736e47f34ce924bb631e.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction.

### VCD

Accuracy: 83.19. Result ID: 69d3736e47f34ce924bb631a.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea5053d.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction.

### DINO-HEAL

Accuracy: 82.95. Result ID: 69d3736e47f34ce924bb631d.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78821e209131cea78bff.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction.

### TCD

Accuracy: 82.67. Result ID: 69d3736e47f34ce924bb631c.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aa31e209131cea84494.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction.

### MemVR

Accuracy: 81.87. Result ID: 69d3736e47f34ce924bb631b.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b01e209131cea74c22.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction.

### Baseline

Accuracy: 81.7. Result ID: 69d3736e47f34ce924bb6319.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction.

### STEAR

Accuracy: 73.19. Result ID: 69d3736e47f34ce924bb6318.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B"}. This record does not assert independent reproduction.

### TCD

Accuracy: 71.51. Result ID: 69d3736e47f34ce924bb6316.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aa31e209131cea84494.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B"}. This record does not assert independent reproduction.

### DINO-HEAL

Accuracy: 71.09. Result ID: 69d3736e47f34ce924bb6317.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78821e209131cea78bff.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B"}. This record does not assert independent reproduction.

### MemVR

Accuracy: 70.69. Result ID: 69d3736e47f34ce924bb6315.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b01e209131cea74c22.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B"}. This record does not assert independent reproduction.

### Baseline

Accuracy: 70.2. Result ID: 69d3736e47f34ce924bb6313.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B"}. This record does not assert independent reproduction.

### VCD

Accuracy: 68.47. Result ID: 69d3736e47f34ce924bb6314.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea5053d.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B"}. This record does not assert independent reproduction.

### STEAR

Accuracy: 65.81. Result ID: 69d3736e47f34ce924bb6312.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-Video-7B"}. This record does not assert independent reproduction.

### MemVR

Accuracy: 65.69. Result ID: 69d3736e47f34ce924bb630f.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b01e209131cea74c22.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-Video-7B"}. This record does not assert independent reproduction.

### DINO-HEAL

Accuracy: 65.58. Result ID: 69d3736e47f34ce924bb6311.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78821e209131cea78bff.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-Video-7B"}. This record does not assert independent reproduction.

### VCD

Accuracy: 65.48. Result ID: 69d3736e47f34ce924bb630e.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea5053d.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-Video-7B"}. This record does not assert independent reproduction.

### TCD

Accuracy: 64.39. Result ID: 69d3736e47f34ce924bb6310.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aa31e209131cea84494.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-Video-7B"}. This record does not assert independent reproduction.

### Baseline

Accuracy: 63.07. Result ID: 69d3736e47f34ce924bb630d.

[Reporting paper](<https://www.sota2.com/research/paper/69d33def7d0172140ec735ff.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA-Video-7B"}. This record does not assert independent reproduction.

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