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 2 · SOTA2 Research

Vulnerability Detection

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

63.72Accuracy

12

Feb 26, 2026

REVEAL Chromium Linux Debian Kernel (test)

0.483Precision

12

Feb 26, 2026

ZK Bug Detection Benchmark

88TP

10

May 26, 2026

0Malicious Verdict Count

9

Jun 2, 2026

SkillVetBench Privilege Abuse

0Malicious Verdict Count

9

Jun 2, 2026

SkillVetBench Supply Chain

0Malicious Verdict Count

9

Jun 2, 2026

SkillVetBench Data Exposure

0Malicious Verdict Count

9

Jun 2, 2026

SkillVetBench Unsafe File Ops

0Malicious Verdict Count

9

Jun 2, 2026

SkillVetBench Prompt Injection

0Malicious Verdict Count

9

Jun 2, 2026

SkillVetBench Command Injection

5Malicious Verdict Count

9

Jun 2, 2026

31 Rust CVE snippets

100Detection Rate

9

May 4, 2026

28 CVEs (Total)

15True Positives (TPs)

8

Jul 2, 2026

Python Vulnerability Detection

99.04F1 Score

8

May 14, 2026

82.7Recall

8

Feb 26, 2026

Security Review Benchmark 100-sample Baseline (C0 + SP0)

Perplexity Sonar Pro

96.1C0 Detection Rate

8

Feb 26, 2026

13.74Execution Time (sec)

8

Feb 26, 2026

3Time (hours)

8

Feb 26, 2026

65.08Precision

8

Feb 26, 2026

Qwen2.5-Coder-7B-Inst

100Precision

8

Feb 26, 2026

Qwen2.5-Coder-7B-Inst

77.39Precision

8

Feb 26, 2026

VulnLLM-R (test)

SuperIntel Defense-LLM

87.3Accuracy

7

May 25, 2026

60.7F1 Score

7

Apr 23, 2026

99.4Accuracy

7

Apr 23, 2026

97Accuracy

7

Apr 23, 2026

285True Positives (TP)

7

Mar 31, 2026

Page 2 of 6

Popular datasets

PrimeVul SkillVetBench Real-world Go bugs dataset Bigvul SARD

Follow for updates

Join SOTA2 Contact