# Grounded Multi-Video Question Answering on WikiVideo

Source: [Grounded Multi-Video Question Answering on WikiVideo](<https://www.sota2.com/research/sota/grounded-multi-video-question-answering-on-wikivideo>)

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

Data updated: 2026-05-20T07:33:40.307Z

Evaluation of model performance on the WikiVideo dataset for the Grounded Multi-Video Question Answering task, reporting Ref and Cite precision, recall, and F1 scores.

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 | Grounded Multi-Video Question Answering |
| Dataset (including any stated split) | WikiVideo |
| Metric | Ref Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [Ref Precision](<https://www.sota2.com/research/sota/grounded-multi-video-question-answering-on-wikivideo.md?metric=Ref%20Precision>): Higher is better; unit: PERCENT.

- [Ref Recall](<https://www.sota2.com/research/sota/grounded-multi-video-question-answering-on-wikivideo.md?metric=Ref%20Recall>): Higher is better; unit: PERCENT.

- [Ref F1](<https://www.sota2.com/research/sota/grounded-multi-video-question-answering-on-wikivideo.md?metric=Ref%20F1>): Higher is better; unit: PERCENT.

- [Cite Precision](<https://www.sota2.com/research/sota/grounded-multi-video-question-answering-on-wikivideo.md?metric=Cite%20Precision>): Higher is better; unit: PERCENT.

- [Cite Recall](<https://www.sota2.com/research/sota/grounded-multi-video-question-answering-on-wikivideo.md?metric=Cite%20Recall>): Higher is better; unit: PERCENT.

- [Cite F1](<https://www.sota2.com/research/sota/grounded-multi-video-question-answering-on-wikivideo.md?metric=Cite%20F1>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/grounded-multi-video-question-answering-on-wikivideo.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Ref Precision | Result date | Report paper |
| --- | --- | --- | --- |
| CRAFT | 94 | Not recorded | 6a0d3feff984739ed6737669 |
| CRAFT | 94 | Not recorded | 6a0d3feff984739ed6737669 |
| CRAFT | 93 | Not recorded | 6a0d3feff984739ed6737669 |
| CRAFT | 87.1 | Not recorded | 6a0d3feff984739ed6737669 |
| CRAFT | 85.9 | Not recorded | 6a0d3feff984739ed6737669 |
| CRAFT | 83.3 | Not recorded | 6a0d3feff984739ed6737669 |
| InternVL-3.5-30B-A3B | 81.5 | Not recorded | 6a0d3feff984739ed6737669 |
| InternVL-3.5-30B-A3B | 80.2 | Not recorded | 6a0d3feff984739ed6737669 |
| Gemma-4-31B | 73.2 | Not recorded | 6a0d3feff984739ed6737669 |
| Gemma-4-31B | 72.1 | Not recorded | 6a0d3feff984739ed6737669 |
| Molmo2-8B | 64.1 | Not recorded | 6a0d3feff984739ed6737669 |

### CRAFT

Ref Precision: 94. Result ID: 6a0d6367fbc373592c05189b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

Recorded evaluation configuration: {"Base VLM":"Qwen3-VL-30B-Instruct","Atomic Claims":"true","Number of Frames":"128"}. This record does not assert independent reproduction.

### CRAFT

Ref Precision: 94. Result ID: 6a0d6367fbc373592c05189e.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

Recorded evaluation configuration: {"Base VLM":"Qwen3-VL-30B-Instruct","Frame Sampling":"DKS","Number of Frames":"32"}. This record does not assert independent reproduction.

### CRAFT

Ref Precision: 93. Result ID: 6a0d6367fbc373592c05189d.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

Recorded evaluation configuration: {"Base VLM":"Qwen3-VL-30B-Instruct","Frame Sampling":"uniform","Number of Frames":"32"}. This record does not assert independent reproduction.

### CRAFT

Ref Precision: 87.1. Result ID: 6a0d6367fbc373592c05189c.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

Recorded evaluation configuration: {"Base VLM":"Qwen3-VL-30B-Instruct","ASR access":"true","Number of Frames":"128"}. This record does not assert independent reproduction.

### CRAFT

Ref Precision: 85.9. Result ID: 6a0d6367fbc373592c05189a.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

Recorded evaluation configuration: {"Base VLM":"Qwen3-VL-30B-Instruct","Critic Loop":"true","Number of Frames":"128"}. This record does not assert independent reproduction.

### CRAFT

Ref Precision: 83.3. Result ID: 6a0d6367fbc373592c051899.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

Recorded evaluation configuration: {"Base VLM":"Qwen3-VL-30B-Instruct","Configuration":"Baseline","Number of Frames":"128"}. This record does not assert independent reproduction.

### InternVL-3.5-30B-A3B

Ref Precision: 81.5. Result ID: 6a0d6367fbc373592c051896.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"Number of Frames":"128","ASR access":"true"}. This record does not assert independent reproduction.

### InternVL-3.5-30B-A3B

Ref Precision: 80.2. Result ID: 6a0d6367fbc373592c051895.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"Number of Frames":"128","ASR access":"false"}. This record does not assert independent reproduction.

### Gemma-4-31B

Ref Precision: 73.2. Result ID: 6a0d6367fbc373592c051898.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f11e209131cea5973c.md>)

Recorded evaluation configuration: {"Number of Frames":"128","ASR access":"true"}. This record does not assert independent reproduction.

### Gemma-4-31B

Ref Precision: 72.1. Result ID: 6a0d6367fbc373592c051897.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f11e209131cea5973c.md>)

Recorded evaluation configuration: {"Number of Frames":"128","ASR access":"false"}. This record does not assert independent reproduction.

### Molmo2-8B

Ref Precision: 64.1. Result ID: 6a0d6367fbc373592c051894.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d3feff984739ed6737669.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6969c61ce25ad2fa9d1eca03.md>)

Recorded evaluation configuration: {"Number of Frames":"128"}. This record does not assert independent reproduction.

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