| Benchmark | Model | Rank | Results |
|---|---|---|---|
| table-question-answering-on-tablebench | Claude-3.7-Sonnet | #6 | EM: 0.612F1: 0.655 |
| table-question-answering-on-tablebench | GPT-4o | #7 | EM: 0.556F1: 0.595 |
| table-question-answering-on-tablebench | MATA (avg. across 10 backbones) | #8 | EM: 0.451F1: 0.482 |
| table-question-answering-on-tablebench | cogito-32b | #9 | EM: 0.440F1: 0.483 |
| table-question-answering-on-tablebench | qwen2.5-3b | #10 | EM: 0.163F1: 0.195 |