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 3 · SOTA2 Research

Vulnerability Detection

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

POWER and CarpetFuzz 24-hour runs

0Total Vulnerabilities

7

Mar 16, 2026

Aggregated Suite (Pygoat, FLASK, DSVW, VAmPI)

100Precision

7

Feb 26, 2026

4TP

7

Feb 26, 2026

10TP

7

Feb 26, 2026

5TP

7

Feb 26, 2026

16TP

7

Feb 26, 2026

SVEN (CWE-125, CWE-190, CWE-416, CWE-476) (test)

72Accuracy

7

Feb 27, 2026

EVMbench Detect

71.7Recall

6

May 12, 2026

Cross-chain projects with known vulnerabilities

95Recall

6

Apr 28, 2026

2Detected Vulnerabilities Count

6

Apr 9, 2026

3Vulnerabilities Detected

6

Apr 9, 2026

5Detected Vulnerabilities Count

6

Apr 9, 2026

3Vuln Count

6

Apr 9, 2026

3Detected Vulnerabilities

6

Apr 9, 2026

6Detected Vulnerabilities Count

6

Apr 9, 2026

3Time (hours)

6

Feb 26, 2026

Top100 Python packages latest

10Score

6

Feb 26, 2026

51 real-world Python applications (test)

100Coverage

5

Jun 23, 2026

role-based agentic workflow (Workflow 1)

44Detection Accuracy

5

Jun 15, 2026

Kotlin PrimeVul pair (test)

45Precision

5

May 12, 2026

NIST Juliet Test Suite

64.4Precision

5

Apr 24, 2026

525True Positives (TP)

5

Mar 31, 2026

Reentrancy source code subset

0RE-Exp

5

Mar 18, 2026

Elysium source code

0RE Error (Exp)

5

Mar 18, 2026

Vulnerability evaluation dataset 1.0 (test)

97.2Opus

5

Feb 26, 2026

Page 3 of 6

Popular datasets

PrimeVul SkillVetBench Real-world Go bugs dataset Bigvul SARD

Follow for updates

Join SOTA2 Contact