Symbolic Chain of Thought Reasoning on TableBench
1.99RgeTableLLM
Evaluation Results
| Method | Links | |
|---|---|---|
| TableLLMModel Scale Group=Comparable2025.12 | 1.99 | |
| Llama-3.1-8BModel Scale Group=Comparable2025.12 | 21.94 | |
| Table-R1-Zero-7BModel Scale Group=Comparable2025.12 | 28.89 | |
| TableGPT2-7BModel Scale Group=Comparable2025.12 | 40.7 | |
| GPT-4oModel Scale Group=Larger2025.12 | 41.43 | |
| Qwen3-8BModel Scale Group=Comparable2025.12 | 41.86 | |
| Qwen-PlusModel Scale Group=Larger2025.12 | 44.06 | |
| QwQ-32BModel Scale Group=Larger2025.12 | 44.84 | |
| Qwen3-72BModel Scale Group=Larger2025.12 | 45.68 | |
| Qwen3-14BModel Scale Group=Larger2025.12 | 47.36 | |
| Qwen3-32BModel Scale Group=Larger2025.12 | 47.47 | |
| TableGPT-R1-8BModel Scale Group=Comparable2025.12 | 49.53 | |
| DeepSeek-V3Model Scale Group=Larger2025.12 | 50.11 |