Tabular Understanding on TableGPT
64.61AccuracyTableDreamer
Evaluation results
| Method | Links | |
|---|---|---|
| TableDreamerIFT Data=27K, Backbone=GPT-4o2025.06 | 64.61 | |
| TableDreamerIFT Data=27K, Backbone=Llama3.1-70B-Instruct2025.06 | 60.57 | |
| GenQAIFT Data=100K2025.06 | 59.87 | |
| Phi3.5-mini-3.8B2025.06 | 59.45 | |
| MagpieIFT Data=100K2025.06 | 57.11 | |
| TableGPT2IFT Data=2.36M, Backbone=Qwen2.5-7B2025.06 | 56.35 | |
| Evol-InstructIFT Data=100K2025.06 | 54.61 | |
| Llama3.1-8B-Instruct2025.06 | 53.39 | |
| MiniCPM3-4B2025.06 | 50.53 | |
| InternLM2.5-7B-Chat2025.06 | 50.22 | |
| DynasourIFT Data=132K2025.06 | 49.71 | |
| DeepSeek-V2-Lite-16B-Chat2025.06 | 49.01 | |
| Self-InstructIFT Data=100K2025.06 | 46.68 | |
| TableLLM-syn-dataIFT Data=80K2025.06 | 46.1 | |
| TableLLMIFT Data=80K, Backbone=CodeLlama-7B2025.06 | 43.11 | |
| GLM4-9B-Chat2025.06 | 39.87 | |
| Mistral-7B-Instruct-v0.32025.06 | 37.92 | |
| Yi-1.5-9B-Chat2025.06 | 31.45 | |
| Baichuan2-7B-Chat2025.06 | 30.31 | |
| TableBenchLLMIFT Data=20K, Backbone=Llama3.1-8B2025.06 | 25.83 | |
| TableGPT-syn-dataIFT Data=66K2025.06 | 25.21 | |
| UCTRIFT Data=43K2025.06 | 17.61 | |
| OmniTabIFT Data=100K2025.06 | 17.53 | |
| ReasTapIFT Data=100K2025.06 | 11.22 |