Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Semantic Parsing research benchmarks – Page 5 · SOTA2 Research

Semantic Parsing

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

SMCalFlow-CS 8-C v1 & v2

Cover-LS (NoFT)

52.5Accuracy (v1)

4

Feb 26, 2026

CFQ Maximum Compound Divergence (MCD)

ROBERTA + DANGLE-ENC

78.3MCD1

4

Feb 26, 2026

HEARTHSTONE (test)

22.7Accuracy

4

Feb 26, 2026

FOR2LAM 0-shot lexical

61Accuracy

3

Feb 26, 2026

100Accuracy

3

Feb 26, 2026

GeoQuery NewFunc

Grammar Prompting (w. oracle grammar)

0.962Exec Acc

3

Feb 26, 2026

GeoQuery Template split

Grammar Prompting (w. oracle grammar)

97.9Execution Accuracy

3

Feb 26, 2026

MCWQ Japanese (Random)

3,440Exact Match

3

Feb 26, 2026

MCWQ-R Japanese (Random)

5,800Exact Match

3

Feb 26, 2026

TOP 500 SPIS v2

74.9Reminder

3

Feb 26, 2026

64.2Reminder Score

3

Feb 26, 2026

ITERATIVE SEARCH + Logical Language Design + Consistency Reward

89.5Accuracy

3

Feb 26, 2026

PMB Dutch 2.2.0 (test)

63.5Precision

3

Feb 26, 2026

PMB German 2.2.0 (test)

66.44Precision

3

Feb 26, 2026

PMB Italian 2.2.0 (test)

0.745Precision

3

Feb 26, 2026

97.3Precision

3

Feb 26, 2026

56.7Reminder Accuracy

2

Feb 26, 2026

Syntax-augmented mBERT

86.2Score (en)

2

Feb 26, 2026

Page 5 of 5

Popular datasets

GEOQUERY SCAN CFQ PMB SMCalFlow

Follow for updates

Join SOTA2 Contact