# Chart Question Answering on FigureQA Alternated Colors (val 2)

Source: [Chart Question Answering on FigureQA Alternated Colors (val 2)](<https://www.sota2.com/research/sota/chart-question-answering-on-figureqa-alternated-colors-val-2>)

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

Data updated: 2026-02-26T05:54:23.442Z

Evaluation of model performance on the Chart Question Answering task using the FigureQA dataset, specifically focusing on the 'Alternated Colors (val 2)' split, utilizing metrics broken down by chart type (vBar, hBar, Pie, Line, Dot-line).

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 | Chart Question Answering |
| Dataset (including any stated split) | FigureQA Alternated Colors (val 2) |
| Metric | Overall Accuracy |
| 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

- [Overall Accuracy](<https://www.sota2.com/research/sota/chart-question-answering-on-figureqa-alternated-colors-val-2.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

- [vBar Score](<https://www.sota2.com/research/sota/chart-question-answering-on-figureqa-alternated-colors-val-2.md?metric=vBar%20Score>): Higher is better; unit: PERCENT.

- [hBar Score](<https://www.sota2.com/research/sota/chart-question-answering-on-figureqa-alternated-colors-val-2.md?metric=hBar%20Score>): Higher is better; unit: PERCENT.

- [Pie Score](<https://www.sota2.com/research/sota/chart-question-answering-on-figureqa-alternated-colors-val-2.md?metric=Pie%20Score>): Higher is better; unit: PERCENT.

- [Line Score](<https://www.sota2.com/research/sota/chart-question-answering-on-figureqa-alternated-colors-val-2.md?metric=Line%20Score>): Higher is better; unit: PERCENT.

- [Dot-line Score](<https://www.sota2.com/research/sota/chart-question-answering-on-figureqa-alternated-colors-val-2.md?metric=Dot-line%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Overall Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PReFIL | 93.26 | Not recorded | 68fa68091e209131cea19b66 |
| RN | 72.54 | Not recorded | 68fa68091e209131cea19b66 |
| IMG+QUES | 57.14 | Not recorded | 68fa68091e209131cea19b66 |
| QUES | 50.01 | Not recorded | 68fa68091e209131cea19b66 |

### PReFIL

Overall Accuracy: 93.26. Result ID: 698d55338b517eb43320b639.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68091e209131cea19b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68091e209131cea19b66.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RN

Overall Accuracy: 72.54. Result ID: 698d55338b517eb43320b638.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68091e209131cea19b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64131e209131cea0294a.md>)

[Implementation](<https://github.com/vmichals/FigureQA-baseline>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### IMG+QUES

Overall Accuracy: 57.14. Result ID: 698d55338b517eb43320b637.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68091e209131cea19b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64131e209131cea0294a.md>)

[Implementation](<https://github.com/vmichals/FigureQA-baseline>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### QUES

Overall Accuracy: 50.01. Result ID: 698d55338b517eb43320b636.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68091e209131cea19b66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64131e209131cea0294a.md>)

[Implementation](<https://github.com/vmichals/FigureQA-baseline>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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