# Video Question Answering on OVO-Bench Real-Time Visual Perception

Source: [Video Question Answering on OVO-Bench Real-Time Visual Perception](<https://www.sota2.com/research/sota/video-question-answering-on-ovo-bench-real-time-visual-perception>)

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

Data updated: 2026-05-11T10:39:53.380Z

Evaluation of model performance on the OVO-Bench Real-Time Visual Perception dataset for Video Question Answering capabilities, reporting metrics including OCR, ACR, ATR, STU, FPD, OJR, and Average.

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 Question Answering |
| Dataset (including any stated split) | OVO-Bench Real-Time Visual Perception |
| Metric | OCR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [OCR](<https://www.sota2.com/research/sota/video-question-answering-on-ovo-bench-real-time-visual-perception.md?metric=OCR>): Higher is better; unit: PERCENT.

- [ACR](<https://www.sota2.com/research/sota/video-question-answering-on-ovo-bench-real-time-visual-perception.md?metric=ACR>): Higher is better; unit: PERCENT.

- [ATR](<https://www.sota2.com/research/sota/video-question-answering-on-ovo-bench-real-time-visual-perception.md?metric=ATR>): Higher is better; unit: PERCENT.

- [STU](<https://www.sota2.com/research/sota/video-question-answering-on-ovo-bench-real-time-visual-perception.md?metric=STU>): Higher is better; unit: PERCENT.

- [FPD](<https://www.sota2.com/research/sota/video-question-answering-on-ovo-bench-real-time-visual-perception.md?metric=FPD>): Higher is better; unit: PERCENT.

- [OJR](<https://www.sota2.com/research/sota/video-question-answering-on-ovo-bench-real-time-visual-perception.md?metric=OJR>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/video-question-answering-on-ovo-bench-real-time-visual-perception.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | OCR | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen2.5-VL-7B + SAVEMem | 91.95 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| Qwen2.5-VL-3B + SAVEMem | 89.26 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| Gemini 1.5 Pro | 85.91 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| ThinkStream | 85.23 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| Qwen2.5-VL-3B | 77.18 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| ViSpeak | 75.2 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| TimeChat-Online | 75.2 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| GPT-4o | 69.8 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| LLaVA-Video | 69.8 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| Qwen2-VL | 69.13 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| InternVL2 | 68.46 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| StreamForest | 68.46 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| Qwen2.5-VL-7B | 67.79 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| Dispider | 57.72 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| LongVU | 55.7 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| Flash-VStream | 25.5 | Not recorded | 6a0162c2dbc836b87d8233d0 |
| VideoLLM-Online | 8.05 | Not recorded | 6a0162c2dbc836b87d8233d0 |

### Qwen2.5-VL-7B + SAVEMem

OCR: 91.95. Result ID: 6a01b08f47f34ce924e44379.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Free"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B + SAVEMem

OCR: 89.26. Result ID: 6a01b08f47f34ce924e44377.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

Recorded evaluation configuration: {"Size":"3B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Free"}. This record does not assert independent reproduction.

### Gemini 1.5 Pro

OCR: 85.91. Result ID: 6a01b08f47f34ce924e44369.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76361e209131cea6be11.md>)

Recorded evaluation configuration: {"Size":"-","Frames":"1 fps","Mode":"Proprietary"}. This record does not assert independent reproduction.

### ThinkStream

OCR: 85.23. Result ID: 6a01b08f47f34ce924e44373.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e730636e5bf4afbdb5e.md>)

Recorded evaluation configuration: {"Size":"3B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B

OCR: 77.18. Result ID: 6a01b08f47f34ce924e44376.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

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

Recorded evaluation configuration: {"Size":"3B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Free"}. This record does not assert independent reproduction.

### ViSpeak

OCR: 75.2. Result ID: 6a01b08f47f34ce924e44372.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77741e209131cea733a6.md>)

Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction.

### TimeChat-Online

OCR: 75.2. Result ID: 6a01b08f47f34ce924e44374.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78311e209131cea771c4.md>)

Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction.

### GPT-4o

OCR: 69.8. Result ID: 6a01b08f47f34ce924e4436a.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a98.md>)

Recorded evaluation configuration: {"Size":"-","Frames":"64","Mode":"Proprietary"}. This record does not assert independent reproduction.

### LLaVA-Video

OCR: 69.8. Result ID: 6a01b08f47f34ce924e4436b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea82934.md>)

[Implementation](<https://llava-vl.github.io/blog/llava-video>)

Recorded evaluation configuration: {"Size":"7B","Frames":"64","Mode":"Offline"}. This record does not assert independent reproduction.

### Qwen2-VL

OCR: 69.13. Result ID: 6a01b08f47f34ce924e4436c.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75151e209131cea65976.md>)

[Implementation](<https://github.com/QwenLM/Qwen2-VL>)

Recorded evaluation configuration: {"Size":"7B","Frames":"64","Mode":"Offline"}. This record does not assert independent reproduction.

### InternVL2

OCR: 68.46. Result ID: 6a01b08f47f34ce924e4436d.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73081e209131cea59f8b.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"Size":"8B","Frames":"64","Mode":"Offline"}. This record does not assert independent reproduction.

### StreamForest

OCR: 68.46. Result ID: 6a01b08f47f34ce924e44375.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bae1e209131cea89d70.md>)

Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

OCR: 67.79. Result ID: 6a01b08f47f34ce924e44378.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

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

Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Free"}. This record does not assert independent reproduction.

### Dispider

OCR: 57.72. Result ID: 6a01b08f47f34ce924e44370.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767f1e209131cea6d744.md>)

[Implementation](<https://github.com/Mark12Ding/Dispider>)

Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction.

### LongVU

OCR: 55.7. Result ID: 6a01b08f47f34ce924e4436e.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75511e209131cea671f3.md>)

[Implementation](<https://github.com/Vision-CAIR/LongVU>)

Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Offline"}. This record does not assert independent reproduction.

### Flash-VStream

OCR: 25.5. Result ID: 6a01b08f47f34ce924e44371.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73ea1e209131cea5ede6.md>)

[Implementation](<https://invinciblwyq.github.io/vstream-page>)

Recorded evaluation configuration: {"Size":"7B","Frames":"1 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction.

### VideoLLM-Online

OCR: 8.05. Result ID: 6a01b08f47f34ce924e4436f.

[Reporting paper](<https://www.sota2.com/research/paper/6a0162c2dbc836b87d8233d0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a71e209131cea5db14.md>)

[Implementation](<https://www.sota2.com/showlab.github.io/videollm-online>)

Recorded evaluation configuration: {"Size":"8B","Frames":"2 fps","Mode":"Online","Training Strategy":"Training-Based"}. This record does not assert independent reproduction.

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