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

Table-based Fact Verification on TabFact

96.7Accuracy

CRAFT w/ Chain-of-Table Extractor

Updated 1mo ago

Evaluation Results

Method	Links
CRAFT w/ Chain-of-Table Extractor 2026.06		96.7
CRAFT 2026.06		96.2
Chain-of-Table 2026.06		96
Dater 2026.06		95.9
Table-Critic 2026.06		95.5
Few-Shot 2026.06		95.1
Critic-CoT 2026.06		94.9
End-to-End 2026.06		94.7
Alter 2026.06		94.6
CRAFT 2026.06		94.6
Binder 2026.06		94.5
CRAFT 2026.06		94.2
CRAFT 2026.06		94.1
CRAFT 2026.06		93.9
CRAFT w/ Chain-of-Table Extractor 2026.06		93.6
CRAFT w/ Chain-of-Table Extractor 2026.06		93.6
Table-Critic 2026.06		93.5
Table-Critic 2026.06		93.3
Table-Critic 2026.06		92.9
Chain-of-Table 2026.06		92.7
Critic-CoT 2026.06		92.5
CRAFT w/ Chain-of-Table Extractor 2026.06		92.2
Dater 2026.06		92.1
Chain-of-Table 2026.06		92.1
Table-Critic 2026.06		92.1
TabClaw 2026.06		92.1
CRAFT w/ Chain-of-Table Extractor 2026.06		92
Dater 2026.06		91.9
End-to-End 2026.06		91.8
Few-Shot 2026.06		91.3
Critic-CoT 2026.06		91.3
Alter 2026.06		90.6
Alter 2026.06		90.5
Dater 2026.06		89.9
Chain-of-Table 2026.06		89.9
Critic-CoT 2026.06		89.8
Alter 2026.06		89.8
Dater 2026.06		89.7
Chain-of-Table 2026.06		89.7
Binder 2026.06		89.5
End-to-End 2026.06		88.9
Few-Shot 2026.06		88.9
Critic-CoT 2026.06		88
ReAct 2026.06		87.9
Alter 2026.06		87.4
Binder 2026.06		87
SheetAgent 2026.06		86.8
Few-Shot 2026.06		86
End-to-End 2026.06		85.6
Binder 2026.06		85.4
Binder 2026.06		84
End-to-End 2026.06		83.4
Few-Shot 2026.06		83.1
Chain-of-Table 2026.06		82.8
CFMS 2026.04		81.37
Chain-of-Table 2024.06		80.2
Chain-of-Table 2026.04		80.2
Binder 2026.06		79.9
SpreadsheetLLM 2026.06		79.2
BINDER 2024.06		79.17
Binder 2026.04		79.17
DATER 2024.06		78.01
Dater 2026.04		78.01
NormTab 2026.06		75.7
Vanilla 2026.06		73.4
TableCoT-chatgpt 2024.06		73.1
ReAcTable 2024.06		73.1
Few-Shot QA 2026.04		71.54
End-to-End QA 2026.04		70.45
NormTabTargeted + SQL 2024.06		68.9
CFMS 2026.04		68.53
Chain-of-Table 2026.04		67.24
NormTabBasic + SQL 2024.06		67.1
Chain-of-Thought 2026.04		65.37
Dater 2026.04		65.12
Text-to-SQL 2024.06		64.71
Text-to-SQL 2026.04		64.71
Text-to-SQL 2026.04		64.03
Binder 2026.04		62.76
Text-to-SQL 2024.06		62.32
Few-Shot QA 2026.04		62.01
Chain-of-Thought 2026.04		60.52
TableDreamer 2025.06		57.65
TableGPT2 2025.06		54.87
TableDreamer 2025.06		49.98
Llama3.1-8B-Instruct 2025.06		48.94
InternLM2.5-7B-Chat 2025.06		47.33
Yi-1.5-9B-Chat 2025.06		46.22
Evol-Instruct 2025.06		45.61
Self-Instruct 2025.06		45.07
End-to-End QA 2026.04		44.86
Magpie 2025.06		43.83
Phi3.5-mini-3.8B 2025.06		43.37
Mistral-7B-Instruct-v0.3 2025.06		42.68
MiniCPM3-4B 2025.06		42.33
Dynasour 2025.06		41.01
GenQA 2025.06		39.38
DeepSeek-V2-Lite-16B-Chat 2025.06		37.11
TableLLM-syn-data 2025.06		29.24
TableLLM 2025.06		27.55

Showing 100 of 107 rows