# Figure Visual Question Answering on FigureQA 1.0 (test 2) Source: [Figure Visual Question Answering on FigureQA 1.0 (test 2)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:23.834Z Evaluation of model performance on the test 2 split of the FigureQA 1.0 dataset, focusing on visual question answering related to figures, often broken down by chart type. 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 | Figure Visual Question Answering | | Dataset (including any stated split) | FigureQA 1.0 (test 2) | | Metric | Overall Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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](): Higher is better; unit: PERCENT. - [Accuracy (Vertical Bar)](): Higher is better; unit: PERCENT. - [Accuracy (Horizontal Bar)](): Higher is better; unit: PERCENT. - [Accuracy (Pie Chart)](): Higher is better; unit: PERCENT. - [Accuracy (Line Chart)](): Higher is better; unit: PERCENT. - [Accuracy (Dot-Line Chart)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Accuracy | Result date | Report paper | | --- | --- | --- | --- | | PREFIL | 93.16 | Not recorded | 68fa6c141e209131cea31fef | | PReFIL | 92.79 | Not recorded | 68fa68091e209131cea19b66 | | Human | 91.21 | Not recorded | 68fa68091e209131cea19b66 | | VisionTaPas | 90.64 | Not recorded | 68fa6c141e209131cea31fef | | TaPas | 89.57 | Not recorded | 68fa6c141e209131cea31fef | | VL-T5 | 88.18 | Not recorded | 68fa6c141e209131cea31fef | | T5 | 87.57 | Not recorded | 68fa6c141e209131cea31fef | | RN | 72.18 | Not recorded | 68fa68091e209131cea19b66 | | Q+I | 56.04 | Not recorded | 68fa68091e209131cea19b66 | ### PREFIL Overall Accuracy: 93.16. Result ID: 698eca06ffc3901de0a131f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data Table Setting":"Gold Data Table Not Provided"}. This record does not assert independent reproduction. ### PReFIL Overall Accuracy: 92.79. Result ID: 698d55338b517eb43320b62e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Human Overall Accuracy: 91.21. Result ID: 698d55338b517eb43320b631. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VisionTaPas Overall Accuracy: 90.64. Result ID: 698eca06ffc3901de0a131f5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Data Table Setting":"Gold Data Table Not Provided"}. This record does not assert independent reproduction. ### TaPas Overall Accuracy: 89.57. Result ID: 698eca06ffc3901de0a131f4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Data Table Setting":"Gold Data Table Not Provided"}. This record does not assert independent reproduction. ### VL-T5 Overall Accuracy: 88.18. Result ID: 698eca06ffc3901de0a131f7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Data Table Setting":"Gold Data Table Not Provided"}. This record does not assert independent reproduction. ### T5 Overall Accuracy: 87.57. Result ID: 698eca06ffc3901de0a131f6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Data Table Setting":"Gold Data Table Not Provided"}. This record does not assert independent reproduction. ### RN Overall Accuracy: 72.18. Result ID: 698d55338b517eb43320b630. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Q+I Overall Accuracy: 56.04. Result ID: 698d55338b517eb43320b62f. [Reporting paper]() [Method origin paper]() [Implementation]() 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.