# Descriptive Visual Question Answering on CharXiv

Source: [Descriptive Visual Question Answering on CharXiv](<https://www.sota2.com/research/sota/descriptive-visual-question-answering-on-charxiv>)

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

Data updated: 2026-03-16T10:15:16.414Z

Evaluation of model performance on the CharXiv dataset for Descriptive Visual Question Answering, reporting 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 | Descriptive Visual Question Answering |
| Dataset (including any stated split) | CharXiv |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| dots.mocr | 77.4 | Not recorded | 69b78e790636e5bf4afbdbbc |
| Qwen3-VL-4B-Instruct | 76.2 | Not recorded | 69b78e790636e5bf4afbdbbc |
| Qwen3-VL-2B-Instruct | 62.3 | Not recorded | 69b78e790636e5bf4afbdbbc |

### dots.mocr

Accuracy: 77.4. Result ID: 69b7d83247f34ce924a0243b.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e790636e5bf4afbdbbc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e790636e5bf4afbdbbc.md>)

Recorded evaluation configuration: {"Parameters":"3B"}. This record does not assert independent reproduction.

### Qwen3-VL-4B-Instruct

Accuracy: 76.2. Result ID: 69b7d83247f34ce924a0243a.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e790636e5bf4afbdbbc.md>)

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

Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction.

### Qwen3-VL-2B-Instruct

Accuracy: 62.3. Result ID: 69b7d83247f34ce924a02439.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e790636e5bf4afbdbbc.md>)

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

Recorded evaluation configuration: {"Parameters":"2B"}. This record does not assert independent reproduction.

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