# element-level commonsense VQA on CommonSketch

Source: [element-level commonsense VQA on CommonSketch](<https://www.sota2.com/research/sota/element-level-commonsense-vqa-on-commonsketch>)

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

Data updated: 2026-03-31T12:09:50.602Z

Evaluation of model performance on the CommonSketch dataset for element-level commonsense Visual Question Answering, reporting Precision, Recall, F1 Score, and 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 | element-level commonsense VQA |
| Dataset (including any stated split) | CommonSketch |
| Metric | Precision |
| Unit | PERCENT |
| 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

- [Precision](<https://www.sota2.com/research/sota/element-level-commonsense-vqa-on-commonsketch.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/element-level-commonsense-vqa-on-commonsketch.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/element-level-commonsense-vqa-on-commonsketch.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/element-level-commonsense-vqa-on-commonsketch.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4o | 93.5 | Not recorded | 69cb55790636e5bf4afca37d |
| Qwen2.5-VL | 89.8 | Not recorded | 69cb55790636e5bf4afca37d |
| mPLUG-Owl3 | 88.3 | Not recorded | 69cb55790636e5bf4afca37d |
| SmolVLM | 80.8 | Not recorded | 69cb55790636e5bf4afca37d |
| InternVL | 80.4 | Not recorded | 69cb55790636e5bf4afca37d |
| Molmo | 79.8 | Not recorded | 69cb55790636e5bf4afca37d |
| LLaVA | 74.9 | Not recorded | 69cb55790636e5bf4afca37d |
| BLIP | 73.1 | Not recorded | 69cb55790636e5bf4afca37d |
| PaliGemma2 | 67.3 | Not recorded | 69cb55790636e5bf4afca37d |

### GPT-4o

Precision: 93.5. Result ID: 69cbb98d47f34ce924b53b16.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55790636e5bf4afca37d.md>)

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

Recorded evaluation configuration: {"Model Type":"Proprietary VLM"}. This record does not assert independent reproduction.

### Qwen2.5-VL

Precision: 89.8. Result ID: 69cbb98d47f34ce924b53b11.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55790636e5bf4afca37d.md>)

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

Recorded evaluation configuration: {"Model Type":"Open-source VLM","Prompting Strategy":"JSON-formatted predictions"}. This record does not assert independent reproduction.

### mPLUG-Owl3

Precision: 88.3. Result ID: 69cbb98d47f34ce924b53b12.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55790636e5bf4afca37d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa746c1e209131cea61a16.md>)

[Implementation](<https://github.com/X-PLUG/mPLUG-Owl>)

Recorded evaluation configuration: {"Model Type":"Open-source VLM","Prompting Strategy":"JSON-formatted predictions"}. This record does not assert independent reproduction.

### SmolVLM

Precision: 80.8. Result ID: 69cbb98d47f34ce924b53b15.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55790636e5bf4afca37d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77d51e209131cea75788.md>)

Recorded evaluation configuration: {"Model Type":"Open-source VLM","Prompting Strategy":"JSON-formatted predictions"}. This record does not assert independent reproduction.

### InternVL

Precision: 80.4. Result ID: 69cbb98d47f34ce924b53b13.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55790636e5bf4afca37d.md>)

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

Recorded evaluation configuration: {"Model Type":"Open-source VLM","Prompting Strategy":"JSON-formatted predictions"}. This record does not assert independent reproduction.

### Molmo

Precision: 79.8. Result ID: 69cbb98d47f34ce924b53b10.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55790636e5bf4afca37d.md>)

Recorded evaluation configuration: {"Model Type":"Open-source VLM","Prompting Strategy":"JSON-formatted predictions"}. This record does not assert independent reproduction.

### LLaVA

Precision: 74.9. Result ID: 69cbb98d47f34ce924b53b0e.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55790636e5bf4afca37d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

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

Recorded evaluation configuration: {"Model Type":"Open-source VLM","Prompting Strategy":"binary yes/no prompt"}. This record does not assert independent reproduction.

### BLIP

Precision: 73.1. Result ID: 69cbb98d47f34ce924b53b0f.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55790636e5bf4afca37d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30874.md>)

[Implementation](<https://github.com/salesforce/BLIP>)

Recorded evaluation configuration: {"Model Type":"Open-source VLM","Prompting Strategy":"binary yes/no prompt"}. This record does not assert independent reproduction.

### PaliGemma2

Precision: 67.3. Result ID: 69cbb98d47f34ce924b53b14.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55790636e5bf4afca37d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76001e209131cea6ad66.md>)

Recorded evaluation configuration: {"Model Type":"Open-source VLM","Prompting Strategy":"JSON-formatted predictions"}. This record does not assert independent reproduction.

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