# Table Question Answering on MMTU Source: [Table Question Answering on MMTU]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:44.374Z Evaluation of model performance on the MMTU 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) | MMTU | | Metric | Accuracy | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | GPT-5-nano | 90.22 | Not recorded | 69802f5ca8b01e76cc8e1465 | | GPT-5-nano | 85.87 | Not recorded | 69802f5ca8b01e76cc8e1465 | | GPT-oss-20b | 81.52 | Not recorded | 69802f5ca8b01e76cc8e1465 | | GPT-4.1-nano | 79.35 | Not recorded | 69802f5ca8b01e76cc8e1465 | | GPT-4.1-nano | 78.26 | Not recorded | 69802f5ca8b01e76cc8e1465 | | GPT-oss-20b | 77.17 | Not recorded | 69802f5ca8b01e76cc8e1465 | | Ministral-3-8B | 54.35 | Not recorded | 69802f5ca8b01e76cc8e1465 | | QWEN3-8B | 52.17 | Not recorded | 69802f5ca8b01e76cc8e1465 | | Ministral-3-8B | 34.78 | Not recorded | 69802f5ca8b01e76cc8e1465 | | QWEN3-8B | 33.7 | Not recorded | 69802f5ca8b01e76cc8e1465 | ### GPT-5-nano Accuracy: 90.22. Result ID: 699616665698665ec4560652. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Workflow":"Chain-of-Table (Tools)","ST Reward":true,"SR Reward":"RG (TABROUGE)"}. This record does not assert independent reproduction. ### GPT-5-nano Accuracy: 85.87. Result ID: 699616665698665ec4560653. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Workflow":"Tree-of-Table (Tools)","ST Reward":true,"SR Reward":"RG (TABROUGE)"}. This record does not assert independent reproduction. ### GPT-oss-20b Accuracy: 81.52. Result ID: 699616665698665ec4560651. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Workflow":"Tree-of-Table (Tools)","ST Reward":true,"SR Reward":"RG (TABROUGE)"}. This record does not assert independent reproduction. ### GPT-4.1-nano Accuracy: 79.35. Result ID: 699616665698665ec456064e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Workflow":"Chain-of-Table (Tools)","ST Reward":true,"SR Reward":"RG (TABROUGE)"}. This record does not assert independent reproduction. ### GPT-4.1-nano Accuracy: 78.26. Result ID: 699616665698665ec456064f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Workflow":"Tree-of-Table (Tools)","ST Reward":true,"SR Reward":"RG (TABROUGE)"}. This record does not assert independent reproduction. ### GPT-oss-20b Accuracy: 77.17. Result ID: 699616665698665ec4560650. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Workflow":"Chain-of-Table (Tools)","ST Reward":true,"SR Reward":"RG (TABROUGE)"}. This record does not assert independent reproduction. ### Ministral-3-8B Accuracy: 54.35. Result ID: 699616665698665ec456064c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Workflow":"Chain-of-Table (Tools)","ST Reward":true,"SR Reward":"RG (TABROUGE)"}. This record does not assert independent reproduction. ### QWEN3-8B Accuracy: 52.17. Result ID: 699616665698665ec456064a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Workflow":"Chain-of-Table (Tools)","ST Reward":true,"SR Reward":"RG (TABROUGE)"}. This record does not assert independent reproduction. ### Ministral-3-8B Accuracy: 34.78. Result ID: 699616665698665ec456064d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Workflow":"Tree-of-Table (Tools)","ST Reward":true,"SR Reward":"RG (TABROUGE)"}. This record does not assert independent reproduction. ### QWEN3-8B Accuracy: 33.7. Result ID: 699616665698665ec456064b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Workflow":"Tree-of-Table (Tools)","ST Reward":true,"SR Reward":"RG (TABROUGE)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.