# Visual Question Answering on ChartQA (Noise/Corruption Evaluation)

Source: [Visual Question Answering on ChartQA (Noise/Corruption Evaluation)](<https://www.sota2.com/research/sota/visual-question-answering-on-chartqa-noise-corruption-evaluation>)

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

Data updated: 2026-04-24T08:03:31.137Z

Evaluation of model performance on the ChartQA dataset for Visual Question Answering, specifically measuring results across different levels of input noise, blur, weather effects, and digital artifacts.

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) | ChartQA |
| Metric | Score (Noise) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Score (Noise)](<https://www.sota2.com/research/sota/visual-question-answering-on-chartqa-noise-corruption-evaluation.md?metric=Score%20(Noise)>): Higher is better; unit: SCALAR.

- [Score (Blur)](<https://www.sota2.com/research/sota/visual-question-answering-on-chartqa-noise-corruption-evaluation.md?metric=Score%20(Blur)>): Higher is better; unit: SCALAR.

- [Score (Weather)](<https://www.sota2.com/research/sota/visual-question-answering-on-chartqa-noise-corruption-evaluation.md?metric=Score%20(Weather)>): Higher is better; unit: SCALAR.

- [Score (Digital)](<https://www.sota2.com/research/sota/visual-question-answering-on-chartqa-noise-corruption-evaluation.md?metric=Score%20(Digital)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score (Noise) | Result date | Report paper |
| --- | --- | --- | --- |
| Latent Denoising | 26.1 | Not recorded | 69eaf92a55a3c32af89f89e0 |
| Baseline | 23.4 | Not recorded | 69eaf92a55a3c32af89f89e0 |
| Latent Denoising | 15.3 | Not recorded | 69eaf92a55a3c32af89f89e0 |
| Baseline | 13.2 | Not recorded | 69eaf92a55a3c32af89f89e0 |

### Latent Denoising

Score (Noise): 26.1. Result ID: 69eb23c447f34ce924d32ff1.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf92a55a3c32af89f89e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69eaf92a55a3c32af89f89e0.md>)

Recorded evaluation configuration: {"Architecture":"Qwen-2.5-VL","Severity":"5","Method Variant":"Chart"}. This record does not assert independent reproduction.

### Baseline

Score (Noise): 23.4. Result ID: 69eb23c447f34ce924d32ff0.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf92a55a3c32af89f89e0.md>)

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

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

Recorded evaluation configuration: {"Architecture":"Qwen-2.5-VL","Severity":"5","Method Variant":"Chart"}. This record does not assert independent reproduction.

### Latent Denoising

Score (Noise): 15.3. Result ID: 69eb23c447f34ce924d33007.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf92a55a3c32af89f89e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69eaf92a55a3c32af89f89e0.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA+CLIP","Corruption Severity":"5"}. This record does not assert independent reproduction.

### Baseline

Score (Noise): 13.2. Result ID: 69eb23c447f34ce924d33006.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf92a55a3c32af89f89e0.md>)

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

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

Recorded evaluation configuration: {"Backbone":"LLaVA+CLIP","Corruption Severity":"5"}. This record does not assert independent reproduction.

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