Share your thoughts, 1 month free Claude Pro on usSee more

Table Question Answering on TableBench 1.0 (test)

48.46Accuracy

Qwen3-8B

Updated 13d ago

Evaluation Results

Method	Links
Qwen3-8B 2026.05		48.46
Qwen3-8B 2026.05		47.17
Qwen3-8B 2026.05		46.22
Qwen3-4B 2026.05		44.7
Qwen3-8B 2026.05		44.47
Qwen3-8B 2026.05		43.86
Qwen3-4B 2026.05		43.13
Qwen3-8B 2026.05		41.81
Qwen3-8B 2026.05		41.69
Qwen3-4B 2026.05		40.75
Qwen3-4B 2026.05		40.38
Qwen3-8B 2026.05		40.08
Qwen3-4B 2026.05		38.99
Qwen3-4B 2026.05		38.97
DeepSeek-R1-Distill-Llama-8B 2026.05		37.48
Qwen3-4B 2026.05		37.34
Qwen3-4B 2026.05		35.11
DeepSeek-R1-Distill-Llama-8B 2026.05		34.71
TableLLM-Qwen2-7B 2026.05		34.41
DeepSeek-R1-Distill-Llama-8B 2026.05		34.38
Qwen3-1.7B 2026.05		33.68
Qwen2.5-Coder-7B-Instruct 2026.05		33
TableLLM-Qwen2-7B 2026.05		31.81
Qwen2.5-Coder-7B-Instruct 2026.05		31.21
TableLLM-Qwen2-7B 2026.05		30.78
Qwen3-1.7B 2026.05		30.76
TableLLM-Qwen2-7B 2026.05		30.52
Qwen2.5-Coder-7B-Instruct 2026.05		30.29
TableLLM-Qwen2-7B 2026.05		30.2
TableLLM-DeepseekCoder-7B 2026.05		30.06
Qwen3-1.7B 2026.05		29.03
Qwen3-1.7B 2026.05		29.02
TableLLM-Llama3.1-8B 2026.05		28.4
DeepSeek-R1-Distill-Llama-8B 2026.05		28
Qwen2.5-Coder-7B-Instruct 2026.05		27.74
DeepSeek-R1-Distill-Llama-8B 2026.05		27.63
TableLLM-Llama3-8B 2026.05		27.61
DeepSeek-R1-Distill-Llama-8B 2026.05		27.56
TableLLM-DeepseekCoder-7B 2026.05		27.21
DeepSeek-R1-Distill-Llama-8B 2026.05		27.2
TableLLM-Qwen2-7B 2026.05		27.02
Qwen3-1.7B 2026.05		26.9
TableGPT2-7B 2026.05		26.65
DeepSeek-R1-Distill-Llama-8B 2026.05		26.31
TableLLM-Llama3.1-8B 2026.05		25.68
Qwen2-7B-Instruct 2026.05		25.51
Qwen2.5-7B-Instruct 2026.05		25.31
TableLLM-DeepseekCoder-7B 2026.05		25
Qwen2-7B-Instruct 2026.05		24.96
Qwen2.5-7B-Instruct 2026.05		24.91
Qwen2.5-7B-Instruct 2026.05		24.88
TableLLM-CodeQwen-7B 2026.05		24.78
TableLLM-DeepseekCoder-7B 2026.05		24.78
Qwen3-1.7B 2026.05		24.65
TableLLM-Qwen2-7B 2026.05		24.4
Meta-Llama-3-8B-Instruct 2026.05		23.44
Meta-Llama-3-8B-Instruct 2026.05		23.4
TableGPT2-7B 2026.05		22.78
TableLLM-Llama3.1-8B 2026.05		22.72
TableLLM-Qwen2-7B 2026.05		22.72
Qwen2.5-Coder-7B-Instruct 2026.05		22.6
TableLLM-DeepseekCoder-7B 2026.05		22.59
TableLLM-Llama3.1-8B 2026.05		22.22
TableLLM-DeepseekCoder-7B 2026.05		21.81
TableLLM-DeepseekCoder-7B 2026.05		21.77
TableLLM-CodeQwen-7B 2026.05		21.74
TableLLM-DeepseekCoder-7B 2026.05		21.65
TableLLM-Llama3.1-8B 2026.05		21.43
TableLLM-Llama3-8B 2026.05		21.4
Qwen2.5-Coder-7B-Instruct 2026.05		21.39
TableLLM-Llama3-8B 2026.05		21.37
TableLLM-Llama3.1-8B 2026.05		21.29
TableLLM-CodeQwen-7B 2026.05		21.28
TableLLM-Llama3.1-8B 2026.05		21.09
TableLLM-Llama3-8B 2026.05		21.01
TableLLM-CodeQwen-7B 2026.05		21
TableLLM-Llama3.1-8B 2026.05		21
TableLLM-Llama3-8B 2026.05		20.98
TableLLM-Llama3-8B 2026.05		20.91
TableLLM-Llama3-8B 2026.05		20.84
Qwen2-7B-Instruct 2026.05		20.75
TableGPT2-7B 2026.05		20.45
Qwen2.5-Coder-7B-Instruct 2026.05		20.39
TableGPT2-7B 2026.05		20.34
TableLLM-CodeQwen-7B 2026.05		20.3
TableLLM-Llama3-8B 2026.05		20.24
TableLLM-CodeQwen-7B 2026.05		20.19
Meta-Llama-3-8B-Instruct 2026.05		19.81
Qwen2.5-7B-Instruct 2026.05		19.71
Meta-Llama-3-8B-Instruct 2026.05		19.19
TableLLM-CodeQwen-7B 2026.05		19.04
Meta-Llama-3-8B-Instruct 2026.05		18.71
Meta-Llama-3-8B-Instruct 2026.05		18.58
Meta-Llama-3-8B-Instruct 2026.05		18.33
TableLLM-CodeQwen-7B 2026.05		18.33
Qwen2.5-7B-Instruct 2026.05		18.24
Qwen2-7B-Instruct 2026.05		18.05
Qwen2.5-7B-Instruct 2026.05		17.91
TableGPT2-7B 2026.05		17.88
Llama-3.1-8B-Instruct 2026.05		17.77

Showing 100 of 136 rows