Table Path Reasoning on Internal Bench
82.7AccuracyTableGPT-R1-8B
Evaluation results
| Method | Links | |
|---|---|---|
| TableGPT-R1-8BModel Scale Group=Comparable Parameter Models2025.12 | 82.7 | |
| Qwen-PlusModel Scale Group=Larger Parameter & Proprietary Models2025.12 | 81.5 | |
| Qwen3-32BModel Scale Group=Larger Parameter & Proprietary Models2025.12 | 78.55 | |
| QwQ-32BModel Scale Group=Larger Parameter & Proprietary Models2025.12 | 75 | |
| Qwen3-14BModel Scale Group=Larger Parameter & Proprietary Models2025.12 | 74.7 | |
| Qwen3-8BModel Scale Group=Comparable Parameter Models2025.12 | 73.9 | |
| DeepSeek-V3Model Scale Group=Larger Parameter & Proprietary Models2025.12 | 72.9 | |
| Qwen3-72BModel Scale Group=Larger Parameter & Proprietary Models2025.12 | 60.5 | |
| Llama-3.1-8BModel Scale Group=Comparable Parameter Models2025.12 | 31.77 | |
| Table-R1-Zero-7BModel Scale Group=Comparable Parameter Models2025.12 | 9.19 | |
| TableLLMModel Scale Group=Comparable Parameter Models2025.12 | 0.65 |