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

Table Fact Verification on TabFact

0.9168Accuracy

Qwen2-72B-Instruct

Updated 4d ago

Evaluation Results

Method	Links
Qwen2-72B-Instruct 2025.02		0.9168	0.5711
GPT-4o 2025.02		0.8762	0.5558
GPT-4o (Image Only) 2025.02		0.8345	0.5426
Qwen2.5-VL-Instruct 2025.02		0.8343	0.5858
Qwen2.5-Instruct 2025.02		0.8308	0.6154
TableLlama + Oracle 2025.02		0.8255	0.5533
MiniCPM-V-2.6 + Vanilla SFT 2025.02		0.8254	0.6193
Qwen2.5-VL-Instruct + HIPPO 2025.02		0.8251	0.629
MiniCPM-V-2.6 + HIPPO 2025.02		0.8227	0.6546
Qwen2.5-VL-Instruct (Image Only) 2025.02		0.8144	0.5685
DocOwl-1.5 2026.02		0.804	-
Qwen2.5-VL-Instruct + Vanilla SFT 2025.02		0.8008	0.6215
TableLlama + Markdown 2025.02		0.7937	0.3786
MiniCPM-V-2.6 2025.02		0.7931	0.6212
MiniCPM-V-2.6 (Image Only) 2025.02		0.7848	0.6042
Llama3.1-Instruct 2025.02		0.7757	0.3542
Table-LLaVA + HIPPO 2025.02		0.7466	0.5552
Llama3-Instruct 2025.02		0.7389	0.3198
HRVDA 2026.02		0.723	-
Table-LLaVA 2025.02		0.6942	0.5098
DocOwl 2026.02		0.676	-
UReader 2026.02		0.676	-
Table-LLaVA (Image Only) 2025.02		0.65	0.3809
PositionOCR 2026.02		0.628	-
Table-LLaVA (Image Only) 2025.02		0.5985	0.3569
Donut 2026.02		0.546	-
TabPedia 2025.02		0.5053	0.2084
Monkey 2025.02		0.2256	0.1416
LLaVA v1.5 2025.02		0.189	0.0982
Llama2 2025.02		0.092	0.1753
mPLUG-Owl2 2025.02		0.0821	0.0776
mPLUG-Owl 2025.02		0.0746	0.0316
Vary-toy 2025.02		0.0633	0.0577
InternLM-XComposer 2025.02		0.0119	0.0077
Qwen-VL 2025.02		0.0112	0.0083
MiniGPT-4 2025.02		0	0.0028