Semantic Parsing on WikiTableQuestions

Metric: Accuracy (Test) (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Accuracy (Test)▼	Extra Data	Paper	Date↕	Code
1	ARTEMIS-DA	80.8	No	ARTEMIS-DA: An Advanced Reasoning and Transforma...	2024-12-18	-
2	TabLaP	76.6	No	Accurate and Regret-aware Numerical Problem Solv...	2024-10-10	Code
3	SynTQA (GPT)	74.4	Yes	SynTQA: Synergistic Table-based Question Answeri...	2024-09-25	Code
4	Mix SC	73.6	No	Rethinking Tabular Data Understanding with Large...	2023-12-27	Code
5	SynTQA (RF)	71.6	Yes	SynTQA: Synergistic Table-based Question Answeri...	2024-09-25	Code
6	CABINET	69.1	No	CABINET: Content Relevance based Noise Reduction...	2024-02-02	Code
7	NormTab+TabSQLify	68.63	No	NormTab: Improving Symbolic Reasoning in LLMs Th...	2024-06-25	Code
8	Chain-of-Table	67.31	No	Chain-of-Table: Evolving Tables in the Reasoning...	2024-01-09	Code
9	Tab-PoT	66.78	No	Efficient Prompting for LLM-based Generative Int...	2024-06-14	-
10	Dater	65.9	No	Large Language Models are Versatile Decomposers:...	2023-01-31	Code
11	LEVER	65.8	No	LEVER: Learning to Verify Language-to-Code Gener...	2023-02-16	Code
12	TabSQLify (col+row)	64.7	No	TabSQLify: Enhancing Reasoning Capabilities of L...	2024-04-15	Code
13	Binder	64.6	No	Binding Language Models in Symbolic Languages	2022-10-06	Code
14	OmniTab-Large	63.3	No	OmniTab: Pretraining with Natural and Synthetic ...	2022-07-08	Code
15	NormTab (Targeted) + SQL	61.2	No	NormTab: Improving Symbolic Reasoning in LLMs Th...	2024-06-25	Code
16	ReasTAP-Large	58.7	No	ReasTAP: Injecting Table Reasoning Skills During...	2022-10-22	Code
17	TAPEX-Large	57.5	No	TAPEX: Table Pre-training via Learning a Neural ...	2021-07-16	Code
18	MAPO + TABERTLarge (K = 3)	51.8	No	TaBERT: Pretraining for Joint Understanding of T...	2020-05-17	Code
19	T5-3b(UnifiedSKG)	49.29	No	UnifiedSKG: Unifying and Multi-Tasking Structure...	2022-01-16	Code
20	TAPAS-Large (pre-trained on SQA)	48.8	Yes	TAPAS: Weakly Supervised Table Parsing via Pre-t...	2020-04-05	Code
21	Structured Attention	44.5	No	Learning Semantic Parsers from Denotations with ...	2019-09-09	Code

#1ARTEMIS-DASOTA
80.8
Accuracy (Test)· 2024-12-18
ARTEMIS-DA: An Advanced Reasoning and Transformation Engine for Multi-Step Insight Synthesis in Data Analytics
#2TabLaPSOTA
76.6
Accuracy (Test)· 2024-10-10
Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering Code
#3SynTQA (GPT)SOTA
74.4
Accuracy (Test)· Extra Data· 2024-09-25
SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA Code
#4Mix SCSOTA
73.6
Accuracy (Test)· 2023-12-27
Rethinking Tabular Data Understanding with Large Language Models Code
#5SynTQA (RF)
71.6
Accuracy (Test)· Extra Data· 2024-09-25
SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA Code
#6CABINET
69.1
Accuracy (Test)· 2024-02-02
CABINET: Content Relevance based Noise Reduction for Table Question Answering Code
#7NormTab+TabSQLify
68.63
Accuracy (Test)· 2024-06-25
NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization Code
#8Chain-of-Table
67.31
Accuracy (Test)· 2024-01-09
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding Code
#9Tab-PoT
66.78
Accuracy (Test)· 2024-06-14
Efficient Prompting for LLM-based Generative Internet of Things
#10DaterSOTA
65.9
Accuracy (Test)· 2023-01-31
Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning Code
#11LEVER
65.8
Accuracy (Test)· 2023-02-16
LEVER: Learning to Verify Language-to-Code Generation with Execution Code
#12TabSQLify (col+row)
64.7
Accuracy (Test)· 2024-04-15
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition Code
#13BinderSOTA
64.6
Accuracy (Test)· 2022-10-06
Binding Language Models in Symbolic Languages Code
#14OmniTab-LargeSOTA
63.3
Accuracy (Test)· 2022-07-08
OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering Code
#15NormTab (Targeted) + SQL
61.2
Accuracy (Test)· 2024-06-25
NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization Code
#16ReasTAP-Large
58.7
Accuracy (Test)· 2022-10-22
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples Code
#17TAPEX-LargeSOTA
57.5
Accuracy (Test)· 2021-07-16
TAPEX: Table Pre-training via Learning a Neural SQL Executor Code
#18MAPO + TABERTLarge (K = 3)SOTA
51.8
Accuracy (Test)· 2020-05-17
TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data Code
#19T5-3b(UnifiedSKG)
49.29
Accuracy (Test)· 2022-01-16
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models Code
#20TAPAS-Large (pre-trained on SQA)SOTA
48.8
Accuracy (Test)· Extra Data· 2020-04-05
TAPAS: Weakly Supervised Table Parsing via Pre-training Code
#21Structured AttentionSOTA
44.5
Accuracy (Test)· 2019-09-09
Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs Code