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

Vulnerability Detection research benchmarks – Page 5 · SOTA2 Research

Vulnerability Detection

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Vulnerable MCP Server Dataset

120True Positives

3

May 21, 2026

Benign MCP Server

124True Negatives (TN)

3

May 21, 2026

Cross-Chain Wild Dataset

128Total Alerts

3

Apr 28, 2026

Existing MEVuls Immunefi and DeFi projects (Representative Results)

94F-score

3

Apr 21, 2026

C/C++ 138 vulnerabilities (test)

108TP (True Positives)

3

Apr 14, 2026

95.39Accuracy

3

Apr 2, 2026

92.59Accuracy

3

Apr 2, 2026

87.63Accuracy

3

Apr 2, 2026

Agent-Vuln-Bench (AVB) (42 vulnerabilities)

40True Positives

3

Mar 25, 2026

1Unique Vulnerabilities

3

Mar 9, 2026

Fuzztruction-Net

0Unique Vulnerability Count

3

Mar 9, 2026

3Execution Time (hours)

3

Feb 26, 2026

PrimeVul Full code samples (Paired)

96.83Accuracy

3

Feb 27, 2026

28 Real-world Logic Vulnerabilities Repositories (CVE dataset)

15True Positives

2

Jul 2, 2026

General Domain-Specific Vulnerability Detection

99F1 Score

2

May 14, 2026

75Precision

2

May 5, 2026

83.9Detection Rate

2

May 4, 2026

Sherlock Ethereum Fusaka Audit Contest

102Total Findings

2

Apr 30, 2026

JS proto 11 vulnerabilities (test)

10TP

2

Apr 14, 2026

PHP type 6 vulnerabilities (test)

6True Positives (TP)

2

Apr 14, 2026

C/C++ UAF 5 vulnerabilities (test)

4TP

2

Apr 14, 2026

All Lang. 343 vulnerabilities (test)

269True Positives (TP)

2

Apr 14, 2026

85,661Tokens

2

Apr 9, 2026

2Vulnerability Count

2

Mar 9, 2026

3Unique Vulnerabilities Found

2

Mar 9, 2026

Page 5 of 6

Popular datasets

PrimeVul SkillVetBench Real-world Go bugs dataset Bigvul SARD

Follow for updates

Join SOTA2 Contact