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

Text-to-SQL research benchmarks – Page 5 · SOTA2 Research

Text-to-SQL

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

WikiSQL 1.0 (dev)

0.855Execution Accuracy

8

Feb 26, 2026

Spider schema presentation perturbations (dev)

95.7AST Similarity (Schema)

7

Apr 10, 2026

Spider 200 question subset with paraphrase perturbations (dev)

0.894AST Similarity (para)

7

Apr 10, 2026

BIRD-147 2023 (test)

97.3SRR

7

Apr 3, 2026

Spider-Syn 1.0 (test)

RESDSQL-3B + NatSQL

69.1Exact Match

7

Feb 26, 2026

Spider-Realistic 1.0 (val)

72.4EM

7

Feb 26, 2026

47Query Accuracy

7

Feb 26, 2026

SCHOLAR template splits (test)

0.22Accuracy

7

Feb 26, 2026

Ambrosia (out-of-domain)

84.4Single Interpretation Coverage

7

Feb 26, 2026

AmbiQT in-domain

92.3Single Interpretation Coverage

7

Feb 26, 2026

5-benchmark aggregate Multi-turn

76.5Accuracy

6

Jun 15, 2026

Average of 5 benchmarks (Spider-dev, Spider-DK, Spider-Realistic, Spider-test, Bird-dev)

70.2Accuracy

6

Jun 15, 2026

Spider2 SQLite 2.0 (test)

57.78Pass@1

6

May 5, 2026

Spider2-Snow 2.0 (test)

55.15Pass@1

6

May 5, 2026

Spider SQLite 2.0 (dev)

15.6Greedy Execution Accuracy

6

Mar 18, 2026

28P@1

6

Feb 26, 2026

Spider Lite 2.0 (full)

57.6Overall EX

6

Feb 26, 2026

Spider lite 2.0 (first 100 queries)

52.4Easy Execution Accuracy

6

Feb 26, 2026

Spider-Syn (test)

72QM (%)

6

Feb 26, 2026

Spider Robustness Suite SYN REALISTIC DK (dev)

78.9Execution Accuracy (SYN)

6

Feb 26, 2026

IoT-SQL (Clean SQL Environment)

63.8Execution Accuracy (EX)

5

May 8, 2026

Spider Snow 2.0

65.44Majority@K

5

May 5, 2026

Text-to-SQL Single-turn Fully-specified

89.3Functional Accuracy

5

Apr 10, 2026

Agentic System (without Fallback)

0Cost Per Query

5

Mar 20, 2026

Spider-DK 1.0 (test)

RESDSQL-3B + NatSQL

53.3EM

5

Feb 26, 2026

Page 5 of 6

Popular datasets

Spider BIRD WikiSQL WTQ ATIS

Follow for updates

Join SOTA2 Contact