Our new X account is live! Follow @wizwand_team for updates

Table Question Answering on HiTab (Acc., Avg.)

64.71Accuracy

TableLlama + Oracle

Updated 3d ago

Evaluation Results

Method	Links
TableLlama + Oracle 2025.02		64.71	55.33
MiniCPM-V-2.6 + HIPPO 2025.02		63	65.46
MiniCPM-V-2.6 + Vanilla SFT 2025.02		62.88	61.93
Qwen2.5-VL-Instruct 2025.02		61.99	58.58
Qwen2.5-VL-Instruct + HIPPO 2025.02		60.97	62.9
Qwen2.5-VL-Instruct + Vanilla SFT 2025.02		59.49	62.15
Qwen2.5-Instruct 2025.02		58.69	61.54
MiniCPM-V-2.6 2025.02		58.56	62.12
Qwen2.5-VL-Instruct (Image Only) 2025.02		56.82	56.85
MiniCPM-V-2.6 (Image Only) 2025.02		56.53	60.42
GPT-4o 2025.02		56.02	55.58
GPT-4o (Image Only) 2025.02		54.82	54.26
Table-LLaVA + HIPPO 2025.02		47.01	55.52
TableLlama + Markdown 2025.02		46.57	37.86
Table-LLaVA 2025.02		44.79	50.98
Qwen2-72B-Instruct 2025.02		39.21	57.11
Table-LLaVA (Image Only) 2025.02		10.85	38.09
Llama2 2025.02		10.72	17.53
Table-LLaVA (Image Only) 2025.02		10.09	35.69
Llama3-Instruct 2025.02		6.97	31.98
Monkey 2025.02		6.41	14.16
TabPedia 2025.02		5.58	20.84
Vary-toy 2025.02		3.42	5.77
LLaVA v1.5 2025.02		2.03	9.82
mPLUG-Owl 2025.02		0.25	3.16
MiniGPT-4 2025.02		0.2	0.28
mPLUG-Owl2 2025.02		0.13	7.76
InternLM-XComposer 2025.02		0.12	0.77
Llama3.1-Instruct 2025.02		0.08	35.42
Qwen-VL 2025.02		0.06	0.83