# Visual Question Answering on GAP-VQA (val)

Source: [Visual Question Answering on GAP-VQA (val)](<https://www.sota2.com/research/sota/visual-question-answering-on-gap-vqa-val>)

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

Data updated: 2026-02-26T05:45:45.762Z

Evaluation of model performance on the validation split of the GAP-VQA dataset for visual question answering capabilities.

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 | Visual Question Answering |
| Dataset (including any stated split) | GAP-VQA (val) |
| Metric | GPT Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [GPT Score](<https://www.sota2.com/research/sota/visual-question-answering-on-gap-vqa-val.md?metric=GPT%20Score>): Higher is better; unit: SCALAR.

- [Improvement](<https://www.sota2.com/research/sota/visual-question-answering-on-gap-vqa-val.md?metric=Improvement>): Higher is better; unit: PERCENT.

## Recorded results

| Method | GPT Score | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4V | 0.637 | Not recorded | 68fa75211e209131cea66027 |
| MiniCPM-Llama3-V-2.5-8B | 0.477 | Not recorded | 68fa75211e209131cea66027 |
| Qwen2-VL-2B | 0.285 | Not recorded | 68fa75211e209131cea66027 |
| Qwen2-VL-7B | 0.25 | Not recorded | 68fa75211e209131cea66027 |
| Qwen2-VL-7B | 0.207 | Not recorded | 68fa75211e209131cea66027 |
| Qwen2-VL-2B | 0.169 | Not recorded | 68fa75211e209131cea66027 |
| MiniCPM-Llama3-V-2.5-8B | 0.147 | Not recorded | 68fa75211e209131cea66027 |

### GPT-4V

GPT Score: 0.637. Result ID: 6993761b3a6c314849161bcf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

Recorded evaluation configuration: {"training\_status":"Pre-fine-tuning"}. This record does not assert independent reproduction.

### MiniCPM-Llama3-V-2.5-8B

GPT Score: 0.477. Result ID: 6993761b3a6c314849161bd1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

Recorded evaluation configuration: {"training\_status":"Post-fine-tuning","method":"GAP-VQA"}. This record does not assert independent reproduction.

### Qwen2-VL-2B

GPT Score: 0.285. Result ID: 6993761b3a6c314849161bd3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

Recorded evaluation configuration: {"training\_status":"Post-fine-tuning","method":"GAP-VQA"}. This record does not assert independent reproduction.

### Qwen2-VL-7B

GPT Score: 0.25. Result ID: 6993761b3a6c314849161bd5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

Recorded evaluation configuration: {"training\_status":"Post-fine-tuning","method":"GAP-VQA"}. This record does not assert independent reproduction.

### Qwen2-VL-7B

GPT Score: 0.207. Result ID: 6993761b3a6c314849161bd4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

Recorded evaluation configuration: {"training\_status":"Pre-fine-tuning"}. This record does not assert independent reproduction.

### Qwen2-VL-2B

GPT Score: 0.169. Result ID: 6993761b3a6c314849161bd2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

Recorded evaluation configuration: {"training\_status":"Pre-fine-tuning"}. This record does not assert independent reproduction.

### MiniCPM-Llama3-V-2.5-8B

GPT Score: 0.147. Result ID: 6993761b3a6c314849161bd0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66027.md>)

Recorded evaluation configuration: {"training\_status":"Pre-fine-tuning"}. This record does not assert independent reproduction.

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