# Table Question Answering on ROBUT-WTQ Abbreviation Replacement (test) Source: [Table Question Answering on ROBUT-WTQ Abbreviation Replacement (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:23.905Z Evaluation of model performance on the test split of the ROBUT-WTQ Abbreviation Replacement dataset for Table Question Answering, focusing on robustness metrics. 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 Question Answering | | Dataset (including any stated split) | ROBUT-WTQ Abbreviation Replacement (test) | | Metric | Accuracy (Pre-perturbation) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 (Pre-perturbation)](): Higher is better; unit: PERCENT. - [Accuracy (Post-perturbation)](): Higher is better; unit: PERCENT. - [R-ACC](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Pre-perturbation) | Result date | Report paper | | --- | --- | --- | --- | | TAPEX | 82.9 | Not recorded | 68fa6fdc1e209131cea47b48 | | OmniTab | 82.1 | Not recorded | 68fa6fdc1e209131cea47b48 | | TAPAS | 81.7 | Not recorded | 68fa6fdc1e209131cea47b48 | | TableFormer | 81 | Not recorded | 68fa6fdc1e209131cea47b48 | | GPT-3 | 78.5 | Not recorded | 68fa6fdc1e209131cea47b48 | | OmniTab | 54.8 | Not recorded | 68fa6fdc1e209131cea47b48 | | TAPEX | 50.4 | Not recorded | 68fa6fdc1e209131cea47b48 | | TableFormer | 45.3 | Not recorded | 68fa6fdc1e209131cea47b48 | | TAPAS | 43.4 | Not recorded | 68fa6fdc1e209131cea47b48 | | GPT-3 | 41.5 | Not recorded | 68fa6fdc1e209131cea47b48 | ### TAPEX Accuracy (Pre-perturbation): 82.9. Result ID: 6990ef833a6c314849046818. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction. ### OmniTab Accuracy (Pre-perturbation): 82.1. Result ID: 6990ef833a6c314849046819. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction. ### TAPAS Accuracy (Pre-perturbation): 81.7. Result ID: 6990ef833a6c314849046816. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction. ### TableFormer Accuracy (Pre-perturbation): 81. Result ID: 6990ef833a6c314849046817. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction. ### GPT-3 Accuracy (Pre-perturbation): 78.5. Result ID: 6990ef833a6c31484904681a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Few-shot","Sample Size":"200"}. This record does not assert independent reproduction. ### OmniTab Accuracy (Pre-perturbation): 54.8. Result ID: 6990ef833a6c3148490467e2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction. ### TAPEX Accuracy (Pre-perturbation): 50.4. Result ID: 6990ef833a6c3148490467e1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction. ### TableFormer Accuracy (Pre-perturbation): 45.3. Result ID: 6990ef833a6c3148490467e0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction. ### TAPAS Accuracy (Pre-perturbation): 43.4. Result ID: 6990ef833a6c3148490467df. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction. ### GPT-3 Accuracy (Pre-perturbation): 41.5. Result ID: 6990ef833a6c3148490467e3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Few-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.