# Temporal Video Grounding on QVHighlights TimeLens (test)

Source: [Temporal Video Grounding on QVHighlights TimeLens (test)](<https://www.sota2.com/research/sota/temporal-video-grounding-on-qvhighlights-timelens-test>)

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

Data updated: 2026-02-26T06:01:20.254Z

Evaluation of Temporal Video Grounding performance on the test split of the QVHighlights TimeLens dataset, measured using Recall metrics (R@X) at IoU thresholds 0.3, 0.5, and 0.7.

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 | Temporal Video Grounding |
| Dataset (including any stated split) | QVHighlights TimeLens (test) |
| Metric | Recall @ IoU=0.3 |
| 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

- [Recall @ IoU=0.3](<https://www.sota2.com/research/sota/temporal-video-grounding-on-qvhighlights-timelens-test.md?metric=Recall%20%40%20IoU%3D0.3>): Higher is better; unit: PERCENT.

- [Recall @ IoU=0.5](<https://www.sota2.com/research/sota/temporal-video-grounding-on-qvhighlights-timelens-test.md?metric=Recall%20%40%20IoU%3D0.5>): Higher is better; unit: PERCENT.

- [Recall @ IoU=0.7](<https://www.sota2.com/research/sota/temporal-video-grounding-on-qvhighlights-timelens-test.md?metric=Recall%20%40%20IoU%3D0.7>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Recall @ IoU=0.3 | Result date | Report paper |
| --- | --- | --- | --- |
| Gemini-2.5-Pro | 84.1 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| Gemini-2.5-Flash | 78.2 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| Gemini-2.0-Flash | 76.2 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| Video-OPD | 73.8 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| GPT-5 | 72.4 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| OP-FKD | 71.2 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| OP-RKD | 70.7 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| GRPO | 69.8 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| GPT-4o | 69 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| Time-R1-7B | 65.8 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| VideoChat-R1.5-7B | 62.2 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| MiMo-VL-7B | 57.1 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| TVG-R1-7B | 55.8 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| Qwen2.5-VL-7B | 55 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| Qwen3-VL-8B-Instruct | 46.6 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| VideoChat-Flash-7B | 45.2 | Not recorded | 6982d2dfa8b01e76cc8e9838 |
| VideoChat-R1-7B | 29.3 | Not recorded | 6982d2dfa8b01e76cc8e9838 |

### Gemini-2.5-Pro

Recall @ IoU=0.3: 84.1. Result ID: 6997548c5698665ec4a675a9.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Gemini-2.5-Flash

Recall @ IoU=0.3: 78.2. Result ID: 6997548c5698665ec4a675a8.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Gemini-2.0-Flash

Recall @ IoU=0.3: 76.2. Result ID: 6997548c5698665ec4a675a7.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Video-OPD

Recall @ IoU=0.3: 73.8. Result ID: 6997548c5698665ec4a675b5.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction.

### GPT-5

Recall @ IoU=0.3: 72.4. Result ID: 6997548c5698665ec4a675a6.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### OP-FKD

Recall @ IoU=0.3: 71.2. Result ID: 6997548c5698665ec4a675b3.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction.

### OP-RKD

Recall @ IoU=0.3: 70.7. Result ID: 6997548c5698665ec4a675b2.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

Recorded evaluation configuration: {"backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction.

### GRPO

Recall @ IoU=0.3: 69.8. Result ID: 6997548c5698665ec4a675b4.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"backbone":"Qwen3-VL-8B"}. This record does not assert independent reproduction.

### GPT-4o

Recall @ IoU=0.3: 69. Result ID: 6997548c5698665ec4a675a5.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Time-R1-7B

Recall @ IoU=0.3: 65.8. Result ID: 6997548c5698665ec4a675ad.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79b81e209131cea7f1a6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### VideoChat-R1.5-7B

Recall @ IoU=0.3: 62.2. Result ID: 6997548c5698665ec4a675af.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b8f1e209131cea891be.md>)

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

### MiMo-VL-7B

Recall @ IoU=0.3: 57.1. Result ID: 6997548c5698665ec4a675b0.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79121e209131cea7bfbd.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TVG-R1-7B

Recall @ IoU=0.3: 55.8. Result ID: 6997548c5698665ec4a675ae.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a391e209131cea81ec4.md>)

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

### Qwen2.5-VL-7B

Recall @ IoU=0.3: 55. Result ID: 6997548c5698665ec4a675ab.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

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

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

### Qwen3-VL-8B-Instruct

Recall @ IoU=0.3: 46.6. Result ID: 6997548c5698665ec4a675b1.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

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

### VideoChat-Flash-7B

Recall @ IoU=0.3: 45.2. Result ID: 6997548c5698665ec4a675aa.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fd1e209131cea807ed.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### VideoChat-R1-7B

Recall @ IoU=0.3: 29.3. Result ID: 6997548c5698665ec4a675ac.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2dfa8b01e76cc8e9838.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89767.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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