realvuln v2.0
Dashboard Methodology Dataset Findings Roadmap GitHub ↗
Scanner deep-dive

DeepSeek V4 Flash by DeepSeek ↗

General-Purpose LLM · agentic-v1 · scored on 66/66 repositories. Strict scoring (unfinished repos counted as misses).

51.8
F3 (strict)
53.8
F2 (strict)
49.9%
Recall (strict)
77.6%
Precision
66/66
Repos scored
deepseek-v4-flash
Model
$1
Total cost
137s
Avg latency
§

Per-repository breakdown

Each bar shows true positives, false positives, and misses on one repository; bar length is proportional to that repo's labeled vulnerabilities. Ranked by F2.

True positiveFalse positiveMissed (FN)
pythonssti100 F2 · 100%
intentionally-vulnerable-python-application82 F2 · 81%
vfapi80 F2 · 85%
vulnpy79 F2 · 79%
vulnerable-api75 F2 · 74%
dsvw75 F2 · 72%
dsvpwa74 F2 · 74%
lets-be-bad-guys73 F2 · 69%
insecure-web72 F2 · 74%
dvblab71 F2 · 71%
vampi70 F2 · 73%
python-insecure-app69 F2 · 67%
vulnerable-flask-app67 F2 · 65%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi67 F2 · 64%
python-app66 F2 · 65%
vulnerable-tornado-app66 F2 · 64%
vc-codex-high-seeded-v2-hr-payroll-django64 F2 · 60%
vc-codex-high-seeded-v2-property-management-fastapi64 F2 · 62%
vc-codex-high-seeded-v2-fintech-lending-fastapi63 F2 · 59%
vc-claude-code-seeded-v2-fintech-lending-fastapi62 F2 · 59%
vc-codex-high-seeded-v2-support-desk-fastapi62 F2 · 57%
damn-vulnerable-flask-application61 F2 · 60%
vc-codex-high-seeded-v2-crm-saas-django60 F2 · 56%
vc-kimi-code-seeded-v2-fintech-lending-fastapi58 F2 · 55%
vc-kimi-code-seeded-v2-property-management-fastapi58 F2 · 53%
owasp-web-playground58 F2 · 56%
vc-kimi-code-seeded-v2-legal-case-django57 F2 · 54%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi56 F2 · 52%
vc-kimi-code-seeded-v2-crm-saas-django55 F2 · 52%
vc-kimi-code-seeded-v2-hr-payroll-django55 F2 · 52%
threatbyte55 F2 · 50%
vc-codex-high-seeded-v2-legal-case-django55 F2 · 52%
vc-codex-seeded-v2-marketplace-commerce-fastapi53 F2 · 48%
vc-claude-code-seeded-v2-support-desk-fastapi52 F2 · 47%
vc-codex-seeded-v2-support-desk-fastapi52 F2 · 47%
vc-codex-seeded-v2-property-management-fastapi52 F2 · 48%
vc-codex-seeded-v2-logistics-dispatch-fastapi52 F2 · 47%
vc-claude-code-seeded-v2-legal-case-django50 F2 · 45%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi50 F2 · 45%
vc-codex-high-seeded-v2-healthcare-clinic-django50 F2 · 46%
vc-codex-seeded-v2-crm-saas-django49 F2 · 47%
vc-codex-seeded-v2-hr-payroll-django49 F2 · 44%
vc-claude-code-seeded-v2-education-lms-django48 F2 · 44%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi48 F2 · 45%
vc-codex-seeded-v2-fintech-lending-fastapi48 F2 · 43%
dvpwa47 F2 · 43%
extremely-vulnerable-flask-app47 F2 · 43%
vc-codex-high-seeded-v2-education-lms-django47 F2 · 44%
vc-claude-code-seeded-v2-property-management-fastapi47 F2 · 42%
vc-claude-code-seeded-v2-hr-payroll-django47 F2 · 44%
vc-kimi-code-seeded-v2-support-desk-fastapi47 F2 · 43%
vulnerable-python-apps47 F2 · 45%
vc-claude-code-seeded-v2-crm-saas-django46 F2 · 43%
vc-codex-seeded-v2-legal-case-django46 F2 · 42%
pygoat46 F2 · 42%
vc-kimi-code-seeded-v2-education-lms-django46 F2 · 43%
vc-claude-code-seeded-v2-healthcare-clinic-django46 F2 · 41%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi45 F2 · 41%
damn-vulnerable-graphql-application44 F2 · 40%
vc-kimi-code-seeded-v2-healthcare-clinic-django44 F2 · 40%
vc-codex-seeded-v2-healthcare-clinic-django41 F2 · 37%
vulpy40 F2 · 36%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi39 F2 · 34%
flask-xss36 F2 · 31%
vc-codex-seeded-v2-education-lms-django30 F2 · 26%
djangoat28 F2 · 24%
RepositoryTPFPFNRecall %F2
pythonssti200100.0100.0
intentionally-vulnerable-python-application61181.081.7
vfapi84185.280.5
vulnpy63151778.879.0
vulnerable-api102473.875.2
dsvw192871.674.6
dsvpwa249874.073.8
lets-be-bad-guys172769.572.7
insecure-web74274.171.9
dvblab166671.271.4
vampi117473.370.5
python-insecure-app51366.769.3
vulnerable-flask-app144765.167.0
vc-codex-high-seeded-v2-marketplace-commerce-fastapi164964.066.7
python-app145765.166.2
vulnerable-tornado-app94564.365.5
vc-codex-high-seeded-v2-hr-payroll-django1531060.063.6
vc-codex-high-seeded-v2-property-management-fastapi1661061.563.5
vc-codex-high-seeded-v2-fintech-lending-fastapi1721258.663.0
vc-claude-code-seeded-v2-fintech-lending-fastapi1741258.662.0
vc-codex-high-seeded-v2-support-desk-fastapi1621257.161.5
damn-vulnerable-flask-application95660.060.7
vc-codex-high-seeded-v2-crm-saas-django1431156.059.8
vc-kimi-code-seeded-v2-fintech-lending-fastapi1841554.558.4
vc-kimi-code-seeded-v2-property-management-fastapi1621453.358.0
owasp-web-playground1681256.057.6
vc-kimi-code-seeded-v2-legal-case-django1451253.856.9
vc-codex-high-seeded-v2-logistics-dispatch-fastapi1531451.756.0
vc-kimi-code-seeded-v2-crm-saas-django1451351.855.1
vc-kimi-code-seeded-v2-hr-payroll-django1551451.755.1
threatbyte1321350.054.8
vc-codex-high-seeded-v2-legal-case-django1361252.054.6
vc-codex-seeded-v2-marketplace-commerce-fastapi1421548.353.0
vc-claude-code-seeded-v2-support-desk-fastapi1611847.152.3
vc-codex-seeded-v2-support-desk-fastapi1401646.752.2
vc-codex-seeded-v2-property-management-fastapi1551648.452.1
vc-codex-seeded-v2-logistics-dispatch-fastapi1421646.751.5
vc-claude-code-seeded-v2-legal-case-django1411745.250.4
vc-claude-code-seeded-v2-logistics-dispatch-fastapi1541845.549.7
vc-codex-high-seeded-v2-healthcare-clinic-django1251446.249.6
vc-codex-seeded-v2-crm-saas-django16101847.149.4
vc-codex-seeded-v2-hr-payroll-django1712243.648.9
vc-claude-code-seeded-v2-education-lms-django1431843.848.3
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi1471745.248.3
vc-codex-seeded-v2-fintech-lending-fastapi1622143.248.2
dvpwa1031343.547.4
extremely-vulnerable-flask-app1421842.747.4
vc-codex-high-seeded-v2-education-lms-django1151444.047.4
vc-claude-code-seeded-v2-property-management-fastapi1421942.447.3
vc-claude-code-seeded-v2-hr-payroll-django1271544.447.2
vc-kimi-code-seeded-v2-support-desk-fastapi1231642.947.2
vulnerable-python-apps1081245.547.1
vc-claude-code-seeded-v2-crm-saas-django1251642.946.5
vc-codex-seeded-v2-legal-case-django1461942.446.1
pygoat33114541.945.9
vc-kimi-code-seeded-v2-education-lms-django1271642.945.8
vc-claude-code-seeded-v2-healthcare-clinic-django1241741.445.5
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi1131640.745.1
damn-vulnerable-graphql-application1462240.344.0
vc-kimi-code-seeded-v2-healthcare-clinic-django1251840.043.8
vc-codex-seeded-v2-healthcare-clinic-django1522636.641.4
vulpy2033735.740.4
vc-claude-code-seeded-v2-marketplace-commerce-fastapi1112134.439.3
flask-xss922131.135.6
vc-codex-seeded-v2-education-lms-django932625.729.6
djangoat1383924.427.7
§

Detection by severity

SeverityTPFPFNRecall %
Critical1460994.2
High385136751.2
Medium369354140.5
Low4624053.5
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
XML External Entities3800100.0
Insecure Deserialization4000100.0
HTTP Header Injection200100.0
XPath Injection400100.0
Open Redirect390197.5
Command / OS Injection480296.0
SQL Injection740494.9
Code Injection / RFI320294.1
Path Traversal400490.9
Server-Side Request Forgery3111075.6
Cross-Site Scripting7903171.8
Security Misconfiguration6704559.8
Hardcoded Credentials3603252.9
Sensitive Data Exposure7308247.1
Other302257534.4
Missing Authentication / Authorization1936422.9
Broken Access Control / IDOR1906422.9
Denial of Service30416.8
§

LLM operational metrics

34,689
Avg input tokens
11,146
Avg output tokens
240,407
Avg total tokens
137s
Avg latency / repo
0.8%
JSON repair rate
118
Total runs
±13.1
F2 run-to-run σ
§

Cost

$1
Total cost
$0.01
Cost / run
$0.001
Cost / 100 LOC
133,782
Python LOC scanned
114
Successful runs

← Back to the leaderboard