# Table Question Answering on WikiTableQuestions (WTQ) T (original tables) (sampled subset) Source: [Table Question Answering on WikiTableQuestions (WTQ) T (original tables) (sampled subset)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:23.439Z Evaluation of model performance on a specific sampled subset of the original tables from the WikiTableQuestions (WTQ) dataset for Table 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 Question Answering | | Dataset (including any stated split) | WikiTableQuestions (WTQ) T (original tables) (sampled subset) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 | | --- | --- | --- | --- | | DP&PYAGENT w/ MIX-SC + NORM w/o RESORT | 73.65 | Not recorded | 68fa71a11e209131cea52336 | | DP&PYAGENT w/ MIX-SC | 73.06 | Not recorded | 68fa71a11e209131cea52336 | | DP&PYAGENT w/ MIX-SC + NORM | 72.4 | Not recorded | 68fa71a11e209131cea52336 | | DATER w/ SC | 68.99 | Not recorded | 68fa71a11e209131cea52336 | | DP w/ SC + NORM w/o RESORT | 66.98 | Not recorded | 68fa71a11e209131cea52336 | | DP w/ SC | 66.39 | Not recorded | 68fa71a11e209131cea52336 | | NORM+DP&PYAGENT w/ EVAL | 64.22 | Not recorded | 68fa71a11e209131cea52336 | | DP w/ SC + NORM | 64.1 | Not recorded | 68fa71a11e209131cea52336 | | PYAGENT w/ SC + NORM | 63.77 | Not recorded | 68fa71a11e209131cea52336 | | BINDER | 63.61 | Not recorded | 68fa71a11e209131cea52336 | | PYAGENT w/ SC + NORM w/o RESORT | 62.84 | Not recorded | 68fa71a11e209131cea52336 | | DATER w/o SC | 61.75 | Not recorded | 68fa71a11e209131cea52336 | | PYAGENT w/ SC | 61.39 | Not recorded | 68fa71a11e209131cea52336 | | NORM+DP | 58.66 | Not recorded | 68fa71a11e209131cea52336 | | NORM+PYAGENT | 56.87 | Not recorded | 68fa71a11e209131cea52336 | | BINDER | 55.07 | Not recorded | 68fa71a11e209131cea52336 | | NORM+PYAGENT-OMITTED | 52.45 | Not recorded | 68fa71a11e209131cea52336 | | STRUCTGPT | 51.77 | Not recorded | 68fa71a11e209131cea52336 | ### DP&PYAGENT w/ MIX-SC + NORM w/o RESORT Accuracy: 73.65. Result ID: 6991f2183a6c3148490b9f04. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"DP&PyAgent","Self-consistency":"Mix-SC","Normalization":"NORM","NORM Reordering":"false"}. This record does not assert independent reproduction. ### DP&PYAGENT w/ MIX-SC Accuracy: 73.06. Result ID: 6991f2183a6c3148490b9f02. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"DP&PyAgent","Self-consistency":"Mix-SC"}. This record does not assert independent reproduction. ### DP&PYAGENT w/ MIX-SC + NORM Accuracy: 72.4. Result ID: 6991f2183a6c3148490b9f03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"DP&PyAgent","Self-consistency":"Mix-SC","Normalization":"NORM"}. This record does not assert independent reproduction. ### DATER w/ SC Accuracy: 68.99. Result ID: 6991f2183a6c3148490b9ef6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompting Protocol":"Few-shot","Base Model":"Codex","Self-consistency":"true"}. This record does not assert independent reproduction. ### DP w/ SC + NORM w/o RESORT Accuracy: 66.98. Result ID: 6991f2183a6c3148490b9efe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"Direct Prompting","Self-consistency":"true","Normalization":"NORM","NORM Reordering":"false"}. This record does not assert independent reproduction. ### DP w/ SC Accuracy: 66.39. Result ID: 6991f2183a6c3148490b9efc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"Direct Prompting","Self-consistency":"true"}. This record does not assert independent reproduction. ### NORM+DP&PYAGENT w/ EVAL Accuracy: 64.22. Result ID: 6991f2183a6c3148490b9efb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"DP&PyAgent","Normalization":"NORM","Inference Evaluation":"true"}. This record does not assert independent reproduction. ### DP w/ SC + NORM Accuracy: 64.1. Result ID: 6991f2183a6c3148490b9efd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"Direct Prompting","Self-consistency":"true","Normalization":"NORM"}. This record does not assert independent reproduction. ### PYAGENT w/ SC + NORM Accuracy: 63.77. Result ID: 6991f2183a6c3148490b9f00. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"PyAgent","Self-consistency":"true","Normalization":"NORM"}. This record does not assert independent reproduction. ### BINDER Accuracy: 63.61. Result ID: 6991f2183a6c3148490b9ef3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompting Protocol":"Few-shot","Base Model":"GPT-3.5"}. This record does not assert independent reproduction. ### PYAGENT w/ SC + NORM w/o RESORT Accuracy: 62.84. Result ID: 6991f2183a6c3148490b9f01. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"PyAgent","Self-consistency":"true","Normalization":"NORM","NORM Reordering":"false"}. This record does not assert independent reproduction. ### DATER w/o SC Accuracy: 61.75. Result ID: 6991f2183a6c3148490b9ef5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompting Protocol":"Few-shot","Base Model":"Codex","Self-consistency":"false"}. This record does not assert independent reproduction. ### PYAGENT w/ SC Accuracy: 61.39. Result ID: 6991f2183a6c3148490b9eff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"PyAgent","Self-consistency":"true"}. This record does not assert independent reproduction. ### NORM+DP Accuracy: 58.66. Result ID: 6991f2183a6c3148490b9ef8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"Direct Prompting","Normalization":"NORM"}. This record does not assert independent reproduction. ### NORM+PYAGENT Accuracy: 56.87. Result ID: 6991f2183a6c3148490b9ef9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"PyAgent","Normalization":"NORM"}. This record does not assert independent reproduction. ### BINDER Accuracy: 55.07. Result ID: 6991f2183a6c3148490b9ef4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompting Protocol":"Few-shot","Base Model":"Codex"}. This record does not assert independent reproduction. ### NORM+PYAGENT-OMITTED Accuracy: 52.45. Result ID: 6991f2183a6c3148490b9efa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5","Reasoning Strategy":"PyAgent-Omitted","Normalization":"NORM"}. This record does not assert independent reproduction. ### STRUCTGPT Accuracy: 51.77. Result ID: 6991f2183a6c3148490b9ef7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompting Protocol":"Zero-shot","Base Model":"GPT-3.5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.