| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TableBench, WikiTQ, WikiSQL Aggregated | Table-R1 (w/ RE-SFT & TARPO) | Overall Score55.33 | 31 | 20d ago | |
| MMTU (test) | TAMA-QWen3 | Overall Performance33.9 | 12 | 3mo ago | |
| InfoTabs (test) | TAMA | Accuracy64.54 | 4 | 3mo ago | |
| OOD Table S2 (test) | GPT-4 | ROUGE-L40.38 | 4 | 3mo ago | |
| OOD Table S1 (test) | GPT-4 | Accuracy80.2 | 4 | 3mo ago |