# Table Question Answering on ArcadeQA Source: [Table Question Answering on ArcadeQA]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:42:31.600Z Evaluation of model performance on the ArcadeQA dataset for Table Question Answering capabilities, typically measured using Exact-match accuracy. 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) | ArcadeQA | | Metric | Exact Match 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 - [Exact Match Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Exact Match Accuracy | Result date | Report paper | | --- | --- | --- | --- | | TableRAG | 49.2 | Not recorded | 68fa766b1e209131cea6cdaa | | TableRAG | 46.2 | Not recorded | 68fa766b1e209131cea6cdaa | | ReadSchema | 43.1 | Not recorded | 68fa766b1e209131cea6cdaa | | RandRowSampling | 42.3 | Not recorded | 68fa766b1e209131cea6cdaa | | TableRAG | 42.3 | Not recorded | 68fa766b1e209131cea6cdaa | | RowColRetrieval | 37.7 | Not recorded | 68fa766b1e209131cea6cdaa | | ReadSchema | 32.3 | Not recorded | 68fa766b1e209131cea6cdaa | | ReadSchema | 30.8 | Not recorded | 68fa766b1e209131cea6cdaa | | RowColRetrieval | 30 | Not recorded | 68fa766b1e209131cea6cdaa | | RandRowSampling | 28.5 | Not recorded | 68fa766b1e209131cea6cdaa | | RandRowSampling | 20.8 | Not recorded | 68fa766b1e209131cea6cdaa | | RowColRetrieval | 16.9 | Not recorded | 68fa766b1e209131cea6cdaa | | ReadTable | 5.4 | Not recorded | 68fa766b1e209131cea6cdaa | | ReadTable | 4.6 | Not recorded | 68fa766b1e209131cea6cdaa | | ReadTable | 1.5 | Not recorded | 68fa766b1e209131cea6cdaa | ### TableRAG Exact Match Accuracy: 49.2. Result ID: 69941e553a6c3148491b30c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Language Model":"GPT 3.5 Turbo"}. This record does not assert independent reproduction. ### TableRAG Exact Match Accuracy: 46.2. Result ID: 69941e553a6c3148491b30d1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Language Model":"Mistral Nemo"}. This record does not assert independent reproduction. ### ReadSchema Exact Match Accuracy: 43.1. Result ID: 69941e553a6c3148491b30c4. [Reporting paper]() Recorded evaluation configuration: {"Language Model":"GPT 3.5 Turbo"}. This record does not assert independent reproduction. ### RandRowSampling Exact Match Accuracy: 42.3. Result ID: 69941e553a6c3148491b30c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Language Model":"GPT 3.5 Turbo"}. This record does not assert independent reproduction. ### TableRAG Exact Match Accuracy: 42.3. Result ID: 69941e553a6c3148491b30cc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Language Model":"Gemini 1.0 Pro"}. This record does not assert independent reproduction. ### RowColRetrieval Exact Match Accuracy: 37.7. Result ID: 69941e553a6c3148491b30c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Language Model":"GPT 3.5 Turbo"}. This record does not assert independent reproduction. ### ReadSchema Exact Match Accuracy: 32.3. Result ID: 69941e553a6c3148491b30ce. [Reporting paper]() Recorded evaluation configuration: {"Language Model":"Mistral Nemo"}. This record does not assert independent reproduction. ### ReadSchema Exact Match Accuracy: 30.8. Result ID: 69941e553a6c3148491b30c9. [Reporting paper]() Recorded evaluation configuration: {"Language Model":"Gemini 1.0 Pro"}. This record does not assert independent reproduction. ### RowColRetrieval Exact Match Accuracy: 30. Result ID: 69941e553a6c3148491b30d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Language Model":"Mistral Nemo"}. This record does not assert independent reproduction. ### RandRowSampling Exact Match Accuracy: 28.5. Result ID: 69941e553a6c3148491b30cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Language Model":"Mistral Nemo"}. This record does not assert independent reproduction. ### RandRowSampling Exact Match Accuracy: 20.8. Result ID: 69941e553a6c3148491b30ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Language Model":"Gemini 1.0 Pro"}. This record does not assert independent reproduction. ### RowColRetrieval Exact Match Accuracy: 16.9. Result ID: 69941e553a6c3148491b30cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Language Model":"Gemini 1.0 Pro"}. This record does not assert independent reproduction. ### ReadTable Exact Match Accuracy: 5.4. Result ID: 69941e553a6c3148491b30cd. [Reporting paper]() Recorded evaluation configuration: {"Language Model":"Mistral Nemo"}. This record does not assert independent reproduction. ### ReadTable Exact Match Accuracy: 4.6. Result ID: 69941e553a6c3148491b30c3. [Reporting paper]() Recorded evaluation configuration: {"Language Model":"GPT 3.5 Turbo"}. This record does not assert independent reproduction. ### ReadTable Exact Match Accuracy: 1.5. Result ID: 69941e553a6c3148491b30c8. [Reporting paper]() Recorded evaluation configuration: {"Language Model":"Gemini 1.0 Pro"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.