| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| WikiTQ | GPT-5-nano | Accuracy91.84 | 163 | 1mo ago | |
| WikiTQ (test) | Commented Reasoning Framework + Answer Selector with Table-R1 | Accuracy84.3 | 140 | 2mo ago | |
| TableBench 1.0 (test) | Qwen3-8B | Accuracy48.46 | 136 | 2mo ago | |
| HiTab | Accuracy94.1 | 129 | 25d ago | ||
| WTQ | Accuracy91.25 | 109 | 25d ago | ||
| TABMWP | Qwen3-VL-8B + TABQAWORLD | Accuracy94.97 | 97 | 3mo ago | |
| WikiTableQuestions (test) | TabLaP | Accuracy76.6 | 86 | 4mo ago | |
| NQTables (test) | ReasonBERTT | F1 Score72.5 | 71 | 3mo ago | |
| WikiTQ (dev) | CRAFT | Denotation Acc87.8 | 67 | 1mo ago | |
| NQ-Table | QUIETT | F1 Score80.1 | 63 | 3mo ago | |
| WTQ (test) | T5 + TC + P | Denotation Accuracy64.7 | 62 | 4mo ago | |
| AIT-QA | Accuracy93.5 | 58 | 3mo ago | ||
| WikiSQL | Accuracy92.07 | 55 | 25d ago | ||
| WikiSQL (test) | SYNTQA (Oracle) | Accuracy95.1 | 55 | 4mo ago | |
| HiTab | QUIETT | F1 Score84.41 | 50 | 4mo ago | |
| SequentialQA | QUIETT | F1 Score73 | 50 | 4mo ago | |
| WikiTQ | QUIETT | F1 Score79.8 | 50 | 4mo ago | |
| Financial TableQA | Qwen-2.5-7B | Execution Accuracy85.51 | 48 | 3mo ago | |
| TAT-QA | Qwen3-VL-8B + TABQAWORLD | Accuracy75.88 | 45 | 3mo ago | |
| TableBench | MATA | EM62 | 40 | 4mo ago | |
| Penguins in a Table | SynTQA | EM96.5 | 40 | 4mo ago | |
| HiTab | TableLlama + Oracle | Accuracy64.71 | 30 | 4mo ago | |
| WikiTQ | DataFactory | Accuracy77.2 | 29 | 4mo ago | |
| WikiTable Questions (WTQ) | Qwen3-VL-8B + TABQAWORLD | Accuracy88.89 | 28 | 3mo ago | |
| WikiTableQuestions (WTQ) (test) | MOCA-AGENT | Accuracy81.4 | 26 | 1mo ago |