Table Question Answering on HybridQA (test)
60.86AccuracyTAMA
Evaluation Results
| Method | Links | |
|---|---|---|
| TAMAbackbone=LLaMA 3.1 8B Instruct2025.01 | 60.86 | |
| GPT-42025.01 | 58.6 | |
| GPT-3.52025.01 | 40.22 | |
| LLaMA 3.1 8B Instructstatus=base model2025.01 | 32.83 |
Loading the SOTA2 catalog…