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

DeepSeek V4 Pro by DeepSeek ↗

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

50.3
F3 (strict)
52.3
F2 (strict)
48.3%
Recall (strict)
78.5%
Precision
66/66
Repos scored
deepseek-v4-pro
Model
$11
Total cost
334s
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)
python-app80 F2 · 81%
dsvw78 F2 · 75%
vfapi75 F2 · 74%
insecure-web72 F2 · 70%
vampi71 F2 · 70%
dsvpwa71 F2 · 69%
vulnerable-api70 F2 · 67%
dvblab67 F2 · 64%
pythonssti67 F2 · 67%
vulnpy64 F2 · 60%
vc-codex-high-seeded-v2-education-lms-django63 F2 · 64%
intentionally-vulnerable-python-application62 F2 · 62%
damn-vulnerable-flask-application61 F2 · 58%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi59 F2 · 55%
vc-kimi-code-seeded-v2-legal-case-django57 F2 · 54%
vc-codex-high-seeded-v2-hr-payroll-django57 F2 · 52%
owasp-web-playground56 F2 · 52%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi56 F2 · 52%
vc-kimi-code-seeded-v2-fintech-lending-fastapi56 F2 · 52%
vc-kimi-code-seeded-v2-healthcare-clinic-django56 F2 · 53%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi56 F2 · 52%
vulnerable-flask-app55 F2 · 52%
vc-codex-high-seeded-v2-crm-saas-django55 F2 · 52%
vc-codex-high-seeded-v2-property-management-fastapi55 F2 · 50%
vc-kimi-code-seeded-v2-education-lms-django54 F2 · 50%
vc-kimi-code-seeded-v2-property-management-fastapi54 F2 · 50%
vc-codex-seeded-v2-logistics-dispatch-fastapi54 F2 · 50%
python-insecure-app54 F2 · 50%
vc-claude-code-seeded-v2-legal-case-django54 F2 · 48%
vc-kimi-code-seeded-v2-hr-payroll-django54 F2 · 52%
vc-codex-high-seeded-v2-support-desk-fastapi53 F2 · 50%
vc-codex-high-seeded-v2-legal-case-django53 F2 · 48%
vc-codex-seeded-v2-fintech-lending-fastapi53 F2 · 49%
vc-codex-high-seeded-v2-fintech-lending-fastapi53 F2 · 48%
vc-claude-code-seeded-v2-hr-payroll-django52 F2 · 48%
vc-codex-seeded-v2-property-management-fastapi52 F2 · 48%
vc-claude-code-seeded-v2-fintech-lending-fastapi52 F2 · 48%
vc-claude-code-seeded-v2-support-desk-fastapi51 F2 · 47%
extremely-vulnerable-flask-app51 F2 · 46%
vc-kimi-code-seeded-v2-support-desk-fastapi51 F2 · 46%
vc-claude-code-seeded-v2-crm-saas-django50 F2 · 46%
vc-codex-seeded-v2-legal-case-django50 F2 · 45%
vulnerable-tornado-app50 F2 · 46%
vc-claude-code-seeded-v2-education-lms-django50 F2 · 47%
lets-be-bad-guys50 F2 · 46%
threatbyte49 F2 · 44%
vc-claude-code-seeded-v2-healthcare-clinic-django49 F2 · 45%
pygoat48 F2 · 45%
vc-codex-seeded-v2-crm-saas-django48 F2 · 44%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi48 F2 · 42%
vc-kimi-code-seeded-v2-crm-saas-django48 F2 · 44%
vc-codex-seeded-v2-hr-payroll-django48 F2 · 44%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi47 F2 · 44%
vc-codex-seeded-v2-support-desk-fastapi47 F2 · 43%
vc-codex-high-seeded-v2-healthcare-clinic-django46 F2 · 42%
vc-codex-seeded-v2-marketplace-commerce-fastapi46 F2 · 41%
vulpy45 F2 · 40%
dvpwa44 F2 · 41%
flask-xss44 F2 · 39%
vc-claude-code-seeded-v2-property-management-fastapi44 F2 · 39%
vulnerable-python-apps42 F2 · 38%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi42 F2 · 38%
damn-vulnerable-graphql-application42 F2 · 38%
vc-codex-seeded-v2-healthcare-clinic-django39 F2 · 34%
vc-codex-seeded-v2-education-lms-django35 F2 · 31%
djangoat32 F2 · 29%
RepositoryTPFPFNRecall %F2
python-app175481.080.4
dsvw203775.377.6
vfapi72274.174.6
insecure-web62370.471.9
vampi103470.071.4
dsvpwa2261068.870.6
vulnerable-api91566.770.0
dvblab142863.667.3
pythonssti11166.766.7
vulnpy4883260.063.9
vc-codex-high-seeded-v2-education-lms-django1611964.063.0
intentionally-vulnerable-python-application42361.961.9
damn-vulnerable-flask-application93657.860.6
vc-codex-high-seeded-v2-logistics-dispatch-fastapi1631355.259.3
vc-kimi-code-seeded-v2-legal-case-django1441253.857.4
vc-codex-high-seeded-v2-hr-payroll-django1311252.057.0
owasp-web-playground1541352.456.0
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi1431351.856.0
vc-kimi-code-seeded-v2-fintech-lending-fastapi1731651.555.9
vc-kimi-code-seeded-v2-healthcare-clinic-django1671453.355.9
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi1641551.655.6
vulnerable-flask-app1151052.455.1
vc-codex-high-seeded-v2-crm-saas-django1351252.055.1
vc-codex-high-seeded-v2-property-management-fastapi1311350.055.1
vc-kimi-code-seeded-v2-education-lms-django1431450.054.3
vc-kimi-code-seeded-v2-property-management-fastapi1531550.054.3
vc-codex-seeded-v2-logistics-dispatch-fastapi1541550.054.0
python-insecure-app41450.053.8
vc-claude-code-seeded-v2-legal-case-django1511648.453.6
vc-kimi-code-seeded-v2-hr-payroll-django1591451.753.6
vc-codex-high-seeded-v2-support-desk-fastapi1451450.053.4
vc-codex-high-seeded-v2-legal-case-django1211348.053.1
vc-codex-seeded-v2-fintech-lending-fastapi1841948.652.9
vc-codex-high-seeded-v2-fintech-lending-fastapi1431548.352.6
vc-claude-code-seeded-v2-hr-payroll-django1331448.152.4
vc-codex-seeded-v2-property-management-fastapi1541648.452.4
vc-claude-code-seeded-v2-fintech-lending-fastapi1441548.352.2
vc-claude-code-seeded-v2-support-desk-fastapi1651847.151.0
extremely-vulnerable-flask-app1511745.850.9
vc-kimi-code-seeded-v2-support-desk-fastapi1331546.450.8
vc-claude-code-seeded-v2-crm-saas-django1341546.450.4
vc-codex-seeded-v2-legal-case-django1521845.550.3
vulnerable-tornado-app62846.450.0
vc-claude-code-seeded-v2-education-lms-django1571746.950.0
lets-be-bad-guys1141345.849.7
threatbyte1211444.249.3
vc-claude-code-seeded-v2-healthcare-clinic-django1341644.848.9
pygoat35124344.948.5
vc-codex-seeded-v2-crm-saas-django1541944.148.4
vc-claude-code-seeded-v2-logistics-dispatch-fastapi1401942.447.9
vc-kimi-code-seeded-v2-crm-saas-django1261544.447.6
vc-codex-seeded-v2-hr-payroll-django1762243.647.5
vc-codex-high-seeded-v2-marketplace-commerce-fastapi1151444.047.4
vc-codex-seeded-v2-support-desk-fastapi1341743.347.4
vc-codex-high-seeded-v2-healthcare-clinic-django1151542.345.8
vc-codex-seeded-v2-marketplace-commerce-fastapi1231741.445.8
vulpy2363440.444.7
dvpwa941440.644.0
flask-xss1211838.944.0
vc-claude-code-seeded-v2-property-management-fastapi1332039.443.9
vulnerable-python-apps821437.942.3
vc-claude-code-seeded-v2-marketplace-commerce-fastapi1222037.542.3
damn-vulnerable-graphql-application1442238.042.2
vc-codex-seeded-v2-healthcare-clinic-django1432734.238.7
vc-codex-seeded-v2-education-lms-django1152431.435.3
djangoat1593728.832.4
§

Detection by severity

SeverityTPFPFNRecall %
Critical14011590.3
High391136152.0
Medium351255938.6
Low4004646.5
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
HTTP Header Injection200100.0
XPath Injection400100.0
Open Redirect391197.5
XML External Entities371197.4
SQL Injection740494.9
Command / OS Injection460492.0
Code Injection / RFI310391.2
Insecure Deserialization360490.0
Path Traversal3401077.3
Hardcoded Credentials4512366.2
Server-Side Request Forgery2701465.9
Cross-Site Scripting6504559.1
Security Misconfiguration5305947.3
Sensitive Data Exposure7308247.1
Other306157134.9
Missing Authentication / Authorization2405928.9
Broken Access Control / IDOR1906422.9
Denial of Service703715.9
§

LLM operational metrics

32,943
Avg input tokens
12,064
Avg output tokens
222,097
Avg total tokens
334s
Avg latency / repo
0.0%
JSON repair rate
118
Total runs
±9.6
F2 run-to-run σ
§

Cost

$11
Total cost
$0.10
Cost / run
$0.007
Cost / 100 LOC
133,782
Python LOC scanned
111
Successful runs

← Back to the leaderboard