# Open-ended Chart Question Answering on OpenCQA (test)

Source: [Open-ended Chart Question Answering on OpenCQA (test)](<https://www.sota2.com/research/sota/open-ended-chart-question-answering-on-opencqa-test>)

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

Data updated: 2026-02-26T05:37:09.923Z

Evaluation of model performance on the test split of the OpenCQA dataset for open-ended chart question answering capabilities, measured using BLEU score.

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 | Open-ended Chart Question Answering |
| Dataset (including any stated split) | OpenCQA (test) |
| Metric | BLEU Score |
| Unit | PERCENT |
| 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

- [BLEU Score](<https://www.sota2.com/research/sota/open-ended-chart-question-answering-on-opencqa-test.md?metric=BLEU%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BLEU Score | Result date | Report paper |
| --- | --- | --- | --- |
| UniChart | 14.88 | Not recorded | 68fa70d71e209131cea4d95a |
| VL-T5 | 14.73 | Not recorded | 68fa70d71e209131cea4d95a |
| MatCha | 12.2 | Not recorded | 68fa70d71e209131cea4d95a |
| T5 | 9.28 | Not recorded | 68fa70d71e209131cea4d95a |

### UniChart

BLEU Score: 14.88. Result ID: 69914b1f3a6c31484907194d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95a.md>)

[Implementation](<https://github.com/vis-nlp/UniChart>)

Recorded evaluation configuration: {"evaluation\_protocol":"finetuned"}. This record does not assert independent reproduction.

### VL-T5

BLEU Score: 14.73. Result ID: 69914b1f3a6c31484907194b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea31fef.md>)

[Implementation](<https://github.com/vis-nlp/ChartQA>)

Recorded evaluation configuration: {"evaluation\_protocol":"finetuned"}. This record does not assert independent reproduction.

### MatCha

BLEU Score: 12.2. Result ID: 69914b1f3a6c31484907194c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6b1e209131cea45729.md>)

[Implementation](<https://www.sota2.com/github.com/google-research/google-research/tree/master/deplot>)

Recorded evaluation configuration: {"evaluation\_protocol":"finetuned"}. This record does not assert independent reproduction.

### T5

BLEU Score: 9.28. Result ID: 69914b1f3a6c31484907194a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea31fef.md>)

[Implementation](<https://github.com/vis-nlp/ChartQA>)

Recorded evaluation configuration: {"evaluation\_protocol":"finetuned"}. This record does not assert independent reproduction.

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