Table Question Answering on TableBench 1.0 (test)
48.46AccuracyQwen3-8B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-8BStrategy=TGN, Model Category=General LLMs2026.05 | 48.46 | |
| Qwen3-8BStrategy=ReAct, Model Category=General LLMs2026.05 | 47.17 | |
| Qwen3-8BStrategy=SCoT, Model Category=General LLMs2026.05 | 46.22 | |
| Qwen3-4BStrategy=SCoT, Model Category=General LLMs2026.05 | 44.7 | |
| Qwen3-8BStrategy=ToT-SelfAsk, Model Category=General LLMs2026.05 | 44.47 | |
| Qwen3-8BStrategy=DP, Model Category=General LLMs2026.05 | 43.86 | |
| Qwen3-4BStrategy=TGN, Model Category=General LLMs2026.05 | 43.13 | |
| Qwen3-8BStrategy=ToT, Model Category=General LLMs2026.05 | 41.81 | |
| Qwen3-8BStrategy=CoT, Model Category=General LLMs2026.05 | 41.69 | |
| Qwen3-4BStrategy=ReAct, Model Category=General LLMs2026.05 | 40.75 | |
| Qwen3-4BStrategy=ToT, Model Category=General LLMs2026.05 | 40.38 | |
| Qwen3-8BStrategy=PIP, Model Category=General LLMs2026.05 | 40.08 | |
| Qwen3-4BStrategy=ToT-SelfAsk, Model Category=General LLMs2026.05 | 38.99 | |
| Qwen3-4BStrategy=DP, Model Category=General LLMs2026.05 | 38.97 | |
| DeepSeek-R1-Distill-Llama-8BStrategy=PIP, Model Category=General LLMs2026.05 | 37.48 | |
| Qwen3-4BStrategy=CoT, Model Category=General LLMs2026.05 | 37.34 | |
| Qwen3-4BStrategy=PIP, Model Category=General LLMs2026.05 | 35.11 | |
| DeepSeek-R1-Distill-Llama-8BStrategy=ReAct, Model Category=General LLMs2026.05 | 34.71 | |
| TableLLM-Qwen2-7BStrategy=PIP, Model Category=Fine-tuned LLMs2026.05 | 34.41 | |
| DeepSeek-R1-Distill-Llama-8BStrategy=CoT, Model Category=General LLMs2026.05 | 34.38 | |
| Qwen3-1.7BStrategy=ReAct, Model Category=General LLMs2026.05 | 33.68 | |
| Qwen2.5-Coder-7B-InstructStrategy=CoT, Model Category=General LLMs2026.05 | 33 | |
| TableLLM-Qwen2-7BStrategy=CoT, Model Category=Fine-tuned LLMs2026.05 | 31.81 | |
| Qwen2.5-Coder-7B-InstructStrategy=ReAct, Model Category=General LLMs2026.05 | 31.21 | |
| TableLLM-Qwen2-7BStrategy=ReAct, Model Category=Fine-tuned LLMs2026.05 | 30.78 | |
| Qwen3-1.7BStrategy=PIP, Model Category=General LLMs2026.05 | 30.76 | |
| TableLLM-Qwen2-7BStrategy=ToT, Model Category=Fine-tuned LLMs2026.05 | 30.52 | |
| Qwen2.5-Coder-7B-InstructStrategy=PIP, Model Category=General LLMs2026.05 | 30.29 | |
| TableLLM-Qwen2-7BStrategy=TGN, Model Category=Fine-tuned LLMs2026.05 | 30.2 | |
| TableLLM-DeepseekCoder-7BStrategy=CoT, Model Category=Fine-tuned LLMs2026.05 | 30.06 | |
| Qwen3-1.7BStrategy=TGN, Model Category=General LLMs2026.05 | 29.03 | |
| Qwen3-1.7BStrategy=SCoT, Model Category=General LLMs2026.05 | 29.02 | |
| TableLLM-Llama3.1-8BStrategy=CoT, Model Category=Fine-tuned LLMs2026.05 | 28.4 | |
| DeepSeek-R1-Distill-Llama-8BStrategy=SCoT, Model Category=General LLMs2026.05 | 28 | |
| Qwen2.5-Coder-7B-InstructStrategy=TGN, Model Category=General LLMs2026.05 | 27.74 | |
| DeepSeek-R1-Distill-Llama-8BStrategy=ToT-SelfAsk, Model Category=General LLMs2026.05 | 27.63 | |
| TableLLM-Llama3-8BStrategy=CoT, Model Category=Fine-tuned LLMs2026.05 | 27.61 | |
| DeepSeek-R1-Distill-Llama-8BStrategy=ToT, Model Category=General LLMs2026.05 | 27.56 | |
| TableLLM-DeepseekCoder-7BStrategy=ReAct, Model Category=Fine-tuned LLMs2026.05 | 27.21 | |
| DeepSeek-R1-Distill-Llama-8BStrategy=DP, Model Category=General LLMs2026.05 | 27.2 | |
| TableLLM-Qwen2-7BStrategy=ToT-SelfAsk, Model Category=Fine-tuned LLMs2026.05 | 27.02 | |
| Qwen3-1.7BStrategy=CoT, Model Category=General LLMs2026.05 | 26.9 | |
| TableGPT2-7BStrategy=PIP, Model Category=Fine-tuned LLMs2026.05 | 26.65 | |
| DeepSeek-R1-Distill-Llama-8BStrategy=TGN, Model Category=General LLMs2026.05 | 26.31 | |
| TableLLM-Llama3.1-8BStrategy=ReAct, Model Category=Fine-tuned LLMs2026.05 | 25.68 | |
| Qwen2-7B-InstructStrategy=ReAct, Model Category=General LLMs2026.05 | 25.51 | |
| Qwen2.5-7B-InstructStrategy=PIP, Model Category=General LLMs2026.05 | 25.31 | |
| TableLLM-DeepseekCoder-7BStrategy=TGN, Model Category=Fine-tuned LLMs2026.05 | 25 | |
| Qwen2-7B-InstructStrategy=PIP, Model Category=General LLMs2026.05 | 24.96 | |
| Qwen2.5-7B-InstructStrategy=TGN, Model Category=General LLMs2026.05 | 24.91 | |
| Qwen2.5-7B-InstructStrategy=CoT, Model Category=General LLMs2026.05 | 24.88 | |
| TableLLM-CodeQwen-7BStrategy=CoT, Model Category=Fine-tuned LLMs2026.05 | 24.78 | |
| TableLLM-DeepseekCoder-7BStrategy=ToT, Model Category=Fine-tuned LLMs2026.05 | 24.78 | |
| Qwen3-1.7BStrategy=DP, Model Category=General LLMs2026.05 | 24.65 | |
| TableLLM-Qwen2-7BStrategy=SCoT, Model Category=Fine-tuned LLMs2026.05 | 24.4 | |
| Meta-Llama-3-8B-InstructStrategy=PIP, Model Category=General LLMs2026.05 | 23.44 | |
| Meta-Llama-3-8B-InstructStrategy=ReAct, Model Category=General LLMs2026.05 | 23.4 | |
| TableGPT2-7BStrategy=CoT, Model Category=Fine-tuned LLMs2026.05 | 22.78 | |
| TableLLM-Llama3.1-8BStrategy=ToT-SelfAsk, Model Category=Fine-tuned LLMs2026.05 | 22.72 | |
| TableLLM-Qwen2-7BStrategy=DP, Model Category=Fine-tuned LLMs2026.05 | 22.72 | |
| Qwen2.5-Coder-7B-InstructStrategy=SCoT, Model Category=General LLMs2026.05 | 22.6 | |
| TableLLM-DeepseekCoder-7BStrategy=DP, Model Category=Fine-tuned LLMs2026.05 | 22.59 | |
| TableLLM-Llama3.1-8BStrategy=DP, Model Category=Fine-tuned LLMs2026.05 | 22.22 | |
| TableLLM-DeepseekCoder-7BStrategy=ToT-SelfAsk, Model Category=Fine-tuned LLMs2026.05 | 21.81 | |
| TableLLM-DeepseekCoder-7BStrategy=PIP, Model Category=Fine-tuned LLMs2026.05 | 21.77 | |
| TableLLM-CodeQwen-7BStrategy=ToT-SelfAsk, Model Category=Fine-tuned LLMs2026.05 | 21.74 | |
| TableLLM-DeepseekCoder-7BStrategy=SCoT, Model Category=Fine-tuned LLMs2026.05 | 21.65 | |
| TableLLM-Llama3.1-8BStrategy=TGN, Model Category=Fine-tuned LLMs2026.05 | 21.43 | |
| TableLLM-Llama3-8BStrategy=ToT-SelfAsk, Model Category=Fine-tuned LLMs2026.05 | 21.4 | |
| Qwen2.5-Coder-7B-InstructStrategy=ToT-SelfAsk, Model Category=General LLMs2026.05 | 21.39 | |
| TableLLM-Llama3-8BStrategy=SCoT, Model Category=Fine-tuned LLMs2026.05 | 21.37 | |
| TableLLM-Llama3.1-8BStrategy=PIP, Model Category=Fine-tuned LLMs2026.05 | 21.29 | |
| TableLLM-CodeQwen-7BStrategy=PIP, Model Category=Fine-tuned LLMs2026.05 | 21.28 | |
| TableLLM-Llama3.1-8BStrategy=ToT, Model Category=Fine-tuned LLMs2026.05 | 21.09 | |
| TableLLM-Llama3-8BStrategy=ReAct, Model Category=Fine-tuned LLMs2026.05 | 21.01 | |
| TableLLM-CodeQwen-7BStrategy=DP, Model Category=Fine-tuned LLMs2026.05 | 21 | |
| TableLLM-Llama3.1-8BStrategy=SCoT, Model Category=Fine-tuned LLMs2026.05 | 21 | |
| TableLLM-Llama3-8BStrategy=ToT, Model Category=Fine-tuned LLMs2026.05 | 20.98 | |
| TableLLM-Llama3-8BStrategy=TGN, Model Category=Fine-tuned LLMs2026.05 | 20.91 | |
| TableLLM-Llama3-8BStrategy=PIP, Model Category=Fine-tuned LLMs2026.05 | 20.84 | |
| Qwen2-7B-InstructStrategy=SCoT, Model Category=General LLMs2026.05 | 20.75 | |
| TableGPT2-7BStrategy=TGN, Model Category=Fine-tuned LLMs2026.05 | 20.45 | |
| Qwen2.5-Coder-7B-InstructStrategy=DP, Model Category=General LLMs2026.05 | 20.39 | |
| TableGPT2-7BStrategy=ToT-SelfAsk, Model Category=Fine-tuned LLMs2026.05 | 20.34 | |
| TableLLM-CodeQwen-7BStrategy=ToT, Model Category=Fine-tuned LLMs2026.05 | 20.3 | |
| TableLLM-Llama3-8BStrategy=DP, Model Category=Fine-tuned LLMs2026.05 | 20.24 | |
| TableLLM-CodeQwen-7BStrategy=TGN, Model Category=Fine-tuned LLMs2026.05 | 20.19 | |
| Meta-Llama-3-8B-InstructStrategy=SCoT, Model Category=General LLMs2026.05 | 19.81 | |
| Qwen2.5-7B-InstructStrategy=SCoT, Model Category=General LLMs2026.05 | 19.71 | |
| Meta-Llama-3-8B-InstructStrategy=ToT-SelfAsk, Model Category=General LLMs2026.05 | 19.19 | |
| TableLLM-CodeQwen-7BStrategy=ReAct, Model Category=Fine-tuned LLMs2026.05 | 19.04 | |
| Meta-Llama-3-8B-InstructStrategy=ToT, Model Category=General LLMs2026.05 | 18.71 | |
| Meta-Llama-3-8B-InstructStrategy=TGN, Model Category=General LLMs2026.05 | 18.58 | |
| Meta-Llama-3-8B-InstructStrategy=DP, Model Category=General LLMs2026.05 | 18.33 | |
| TableLLM-CodeQwen-7BStrategy=SCoT, Model Category=Fine-tuned LLMs2026.05 | 18.33 | |
| Qwen2.5-7B-InstructStrategy=ReAct, Model Category=General LLMs2026.05 | 18.24 | |
| Qwen2-7B-InstructStrategy=TGN, Model Category=General LLMs2026.05 | 18.05 | |
| Qwen2.5-7B-InstructStrategy=ToT-SelfAsk, Model Category=General LLMs2026.05 | 17.91 | |
| TableGPT2-7BStrategy=ToT, Model Category=Fine-tuned LLMs2026.05 | 17.88 | |
| Llama-3.1-8B-InstructStrategy=ReAct, Model Category=General LLMs2026.05 | 17.77 |