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

Fact Verification on TabFact

92.1Accuracy

Human

Updated 3d ago

Evaluation Results

Method	Links
Human 2024.04		92.1
TabTrim-8B 2026.01		91.2
PASTA 2024.04		90.8
Table-Critic 2026.01		90.6
TabTrim-4B 2026.01		89.4
Chain-of-Table 2026.01		88.9
TALON 2026.01		87.6
SaMoE 2024.04		86.7
CHAIN-OF-TABLE 2024.01		86.61
TAPEX 2024.04		85.9
DATER 2024.04		85.6
IXC 2.5 2024.09		85.2
BINDER 2024.04		85.1
Dater 2024.01		84.63
Liu et al. (2021) 2022.01		84.2
TaPas 2024.04		83.9
T5-3B 2022.01		83.68
Dater 2026.01		83.6
Binder 2026.01		83.3
ReAcTable 2024.04		83.1
TableLlama+text 2026.02		82.55
T5-large 2022.01		80.85
CHAIN-OF-TABLE 2024.01		80.2
Chain-of-Table 2024.04		80.2
DocOwl 1.5 2024.09		80.2
TabSQLify 2024.04		79.5
Binder 2024.01		79.17
BINDER 2024.04		79.1
Chain-of-Thought 2024.01		79.05
TabSQLify 2024.04		78.5
TabSQLify 2026.01		78.3
DocOwl2 2024.09		78.2
Few-Shot QA 2024.01		78.06
Dater 2024.01		78.01
DATER 2024.04		78
End-to-End QA 2024.01		77.92
GPT-4o-mini 2026.01		77.4
TabSQLify 2024.04		77
Binder 2024.01		76.98
Qwen3-8B 2026.01		76.7
T5-base 2022.01		76.13
SAT 2024.04		75.5
Yang et al. (2020) 2022.01		74.4
LogicFactChecker 2024.04		74.3
Qwen3-4B 2026.01		74.1
ReAcTable 2024.04		73.1
TableCoT 2024.04		73.1
TableCoT 2024.04		72.6
Few-Shot QA 2024.01		71.54
End-to-End QA 2024.01		70.45
Text-to-SQL 2024.01		68.37
Table-BERT 2024.04		68.1
UReader 2024.09		67.6
CHAIN-OF-TABLE 2024.01		67.24
Chain-of-Thought 2024.01		65.37
Dater 2024.01		65.12
Text-to-SQL 2024.01		64.71
Text-to-SQL 2024.01		64.03
Binder 2024.01		62.76
Few-Shot QA 2024.01		62.01
Chain-of-Thought 2024.01		60.52
DocOwl 2024.09		60.2
Table-LLaVA 7B 2026.02		59.85
Re-Table-7B-rerank 2026.02		56.67
Re-Table-7B-retrieval 2026.02		50.64
End-to-End QA 2024.01		44.86
Monkey 2026.02		22.56
LLaVA v1.6 2026.02		19.26
LLaVA v1.5 2026.02		18.9
BLIP2 2026.02		18.62
Vary-toy 2026.02		6.33
Llama2+text 2026.02		4.21
MiniGPT-4 2026.02		0