# Table Visual Question Answering on TabFact (test) Source: [Table Visual Question Answering on TabFact (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:57.604Z Evaluation of model performance on the test split of the TabFact dataset for Table Visual Question Answering. 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 | Table Visual Question Answering | | Dataset (including any stated split) | TabFact (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DocFormerv2large | 0.832 | Not recorded | 68fa6f911e209131cea464e7 | | DocOwl 1.5 | 0.804 | Not recorded | 68fa75301e209131cea663db | | UDOP | 0.789 | Not recorded | 68fa6f911e209131cea464e7 | | T5large+2D+U | 0.786 | Not recorded | 68fa6f911e209131cea464e7 | | LayoutLMv3large | 0.781 | Not recorded | 68fa6f911e209131cea464e7 | | T5large+U | 0.76 | Not recorded | 68fa6f911e209131cea464e7 | | TabPedia | 0.713 | Not recorded | 68fa75301e209131cea663db | | GPT4V | 0.693 | Not recorded | 68fa75301e209131cea663db | | Gemini Pro | 0.679 | Not recorded | 68fa75301e209131cea663db | | Xcomposer2 | 0.623 | Not recorded | 68fa75301e209131cea663db | | T5large | 0.589 | Not recorded | 68fa6f911e209131cea464e7 | | T5large+2D | 0.58 | Not recorded | 68fa6f911e209131cea464e7 | | TextMonkey | 0.536 | Not recorded | 68fa75301e209131cea663db | | Cogagent | 0.517 | Not recorded | 68fa75301e209131cea663db | | Monkey | 0.498 | Not recorded | 68fa75301e209131cea663db | ### DocFormerv2large Accuracy: 0.832. Result ID: 6990caed3a6c3148490352a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"pre-train data":"64M","#param":"750M"}. This record does not assert independent reproduction. ### DocOwl 1.5 Accuracy: 0.804. Result ID: 699377a83a6c3148491625c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Size":1344}. This record does not assert independent reproduction. ### UDOP Accuracy: 0.789. Result ID: 6990caed3a6c3148490352a7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"pre-train data":"11M","#param":"794M"}. This record does not assert independent reproduction. ### T5large+2D+U Accuracy: 0.786. Result ID: 6990caed3a6c3148490352a5. [Reporting paper]() Recorded evaluation configuration: {"#param":"750M"}. This record does not assert independent reproduction. ### LayoutLMv3large Accuracy: 0.781. Result ID: 6990caed3a6c3148490352a6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"pre-train data":"11M","#param":"368M"}. This record does not assert independent reproduction. ### T5large+U Accuracy: 0.76. Result ID: 6990caed3a6c3148490352a3. [Reporting paper]() Recorded evaluation configuration: {"#param":"750M"}. This record does not assert independent reproduction. ### TabPedia Accuracy: 0.713. Result ID: 699377a83a6c3148491625c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input Size":2560}. This record does not assert independent reproduction. ### GPT4V Accuracy: 0.693. Result ID: 699377a83a6c3148491625c1. [Reporting paper]() Recorded evaluation configuration: {"Input Size":645}. This record does not assert independent reproduction. ### Gemini Pro Accuracy: 0.679. Result ID: 699377a83a6c3148491625c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Size":659}. This record does not assert independent reproduction. ### Xcomposer2 Accuracy: 0.623. Result ID: 699377a83a6c3148491625c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input Size":511}. This record does not assert independent reproduction. ### T5large Accuracy: 0.589. Result ID: 6990caed3a6c3148490352a2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#param":"750M"}. This record does not assert independent reproduction. ### T5large+2D Accuracy: 0.58. Result ID: 6990caed3a6c3148490352a4. [Reporting paper]() Recorded evaluation configuration: {"#param":"750M"}. This record does not assert independent reproduction. ### TextMonkey Accuracy: 0.536. Result ID: 699377a83a6c3148491625bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Size":896}. This record does not assert independent reproduction. ### Cogagent Accuracy: 0.517. Result ID: 699377a83a6c3148491625bf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input Size":1120}. This record does not assert independent reproduction. ### Monkey Accuracy: 0.498. Result ID: 699377a83a6c3148491625be. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input Size":896}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.