| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TABLEBENCH | SERO | Accuracy63.48 | 39 | 5d ago | |
| TableBench | Table-R1 (w/ RE-SFT & TARPO) | DP44.54 | 31 | 20d ago | |
| WTQ + FeTaQA + TabFact Combined (test) | RSAT | F1 Score64.7 | 24 | 1mo ago | |
| InfoTabs | TableGPT2 | Accuracy84.72 | 24 | 3mo ago | |
| TableBench | ReAct | Pass@172.52 | 21 | 2mo ago | |
| WikiTQ, TabFact, TableBench, HiTab, FinQA Average | 14B Only | Accuracy75.47 | 18 | 5d ago | |
| FinQA | 14B Only | Accuracy69.4 | 18 | 5d ago | |
| HiTab | 14B Only | Accuracy80.17 | 18 | 5d ago | |
| TabFact | 14B Only | Accuracy90.47 | 18 | 5d ago | |
| WikiTQ | 14B Only | Accuracy84.12 | 18 | 5d ago | |
| WikiTQ | TabTrim-8B | Exact Match (EM)79.4 | 11 | 3mo ago | |
| TabFact S | POTABLE | Accuracy88.93 | 10 | 3mo ago | |
| WikiTQ (T) | POTABLE | Accuracy65.56 | 10 | 3mo ago | |
| WikiTQ (D) | POTABLE | Accuracy0.651 | 10 | 3mo ago | |
| Synthetic dataset | TAPEX | Accuracy79.5 | 6 | 3mo ago | |
| TabFact C | POTABLE | Accuracy82.7 | 5 | 3mo ago |