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

Gemini 3.5 Flash by Google DeepMind ↗

General-Purpose LLM · agentic-v1 · scored on 64/66 repositories. Strict scoring (unfinished repos counted as misses).

34.5
F3 (strict)
37.0
F2 (strict)
32.3%
Recall (strict)
89.8%
Precision
64/66
Repos scored
gemini-3.5-flash
Model
$81
Total cost
175s
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)
intentionally-vulnerable-python-application76 F2 · 71%
vfapi71 F2 · 67%
dvblab67 F2 · 62%
insecure-web60 F2 · 56%
owasp-web-playground53 F2 · 48%
pythonssti52 F2 · 50%
vulnerable-api50 F2 · 45%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi50 F2 · 44%
dsvpwa49 F2 · 44%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi49 F2 · 45%
vampi49 F2 · 44%
vc-codex-high-seeded-v2-property-management-fastapi48 F2 · 44%
python-app48 F2 · 44%
vulnerable-flask-app48 F2 · 43%
vc-codex-seeded-v2-logistics-dispatch-fastapi47 F2 · 42%
threatbyte46 F2 · 42%
vc-codex-high-seeded-v2-crm-saas-django45 F2 · 40%
vc-codex-high-seeded-v2-fintech-lending-fastapi45 F2 · 40%
vc-kimi-code-seeded-v2-fintech-lending-fastapi45 F2 · 39%
vulnerable-python-apps44 F2 · 39%
vc-codex-seeded-v2-fintech-lending-fastapi43 F2 · 38%
vc-kimi-code-seeded-v2-support-desk-fastapi43 F2 · 38%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi43 F2 · 38%
lets-be-bad-guys42 F2 · 38%
vc-kimi-code-seeded-v2-legal-case-django42 F2 · 37%
vc-codex-high-seeded-v2-support-desk-fastapi42 F2 · 37%
vc-codex-high-seeded-v2-healthcare-clinic-django42 F2 · 37%
vc-codex-seeded-v2-marketplace-commerce-fastapi41 F2 · 36%
vc-claude-code-seeded-v2-legal-case-django41 F2 · 35%
vc-claude-code-seeded-v2-crm-saas-django41 F2 · 36%
vc-claude-code-seeded-v2-hr-payroll-django40 F2 · 35%
damn-vulnerable-graphql-application40 F2 · 39%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi40 F2 · 35%
extremely-vulnerable-flask-app40 F2 · 34%
vc-codex-seeded-v2-support-desk-fastapi40 F2 · 34%
vc-kimi-code-seeded-v2-hr-payroll-django39 F2 · 34%
vc-claude-code-seeded-v2-support-desk-fastapi39 F2 · 34%
vc-kimi-code-seeded-v2-crm-saas-django39 F2 · 35%
vc-codex-seeded-v2-legal-case-django38 F2 · 33%
vulnpy38 F2 · 33%
vc-kimi-code-seeded-v2-property-management-fastapi38 F2 · 33%
vc-kimi-code-seeded-v2-education-lms-django38 F2 · 33%
vc-codex-seeded-v2-hr-payroll-django37 F2 · 32%
vc-codex-high-seeded-v2-legal-case-django37 F2 · 32%
vc-claude-code-seeded-v2-healthcare-clinic-django36 F2 · 31%
vc-claude-code-seeded-v2-property-management-fastapi35 F2 · 30%
vulnerable-tornado-app34 F2 · 31%
vc-codex-high-seeded-v2-education-lms-django34 F2 · 29%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi33 F2 · 28%
vc-claude-code-seeded-v2-education-lms-django32 F2 · 27%
vc-codex-high-seeded-v2-hr-payroll-django31 F2 · 28%
vc-codex-seeded-v2-crm-saas-django31 F2 · 26%
pygoat29 F2 · 25%
dvpwa29 F2 · 25%
python-insecure-app29 F2 · 25%
vc-codex-seeded-v2-education-lms-django28 F2 · 24%
vc-codex-seeded-v2-healthcare-clinic-django26 F2 · 22%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi24 F2 · 21%
flask-xss22 F2 · 19%
vc-codex-seeded-v2-property-management-fastapi22 F2 · 19%
vc-claude-code-seeded-v2-fintech-lending-fastapi21 F2 · 19%
djangoat21 F2 · 17%
vulpy19 F2 · 16%
damn-vulnerable-flask-application13 F2 · 11%
RepositoryTPFPFNRecall %F2
intentionally-vulnerable-python-application50271.475.8
vfapi60366.771.3
dvblab141862.166.7
insecure-web51455.659.5
owasp-web-playground1421448.253.0
pythonssti11150.051.9
vulnerable-api60845.250.5
vc-codex-high-seeded-v2-marketplace-commerce-fastapi1101444.049.5
dsvpwa1411843.849.0
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi1451745.248.9
vampi70844.448.8
vc-codex-high-seeded-v2-property-management-fastapi1111543.648.5
python-app931244.448.1
vulnerable-flask-app911242.947.9
vc-codex-seeded-v2-logistics-dispatch-fastapi1201841.747.2
threatbyte1141542.346.4
vc-codex-high-seeded-v2-crm-saas-django1001540.045.2
vc-codex-high-seeded-v2-fintech-lending-fastapi1201839.745.1
vc-kimi-code-seeded-v2-fintech-lending-fastapi1302039.444.8
vulnerable-python-apps801438.643.8
vc-codex-seeded-v2-fintech-lending-fastapi1412337.842.9
vc-kimi-code-seeded-v2-support-desk-fastapi1001837.542.9
vc-codex-high-seeded-v2-logistics-dispatch-fastapi1121837.942.8
lets-be-bad-guys911537.542.5
vc-kimi-code-seeded-v2-legal-case-django1001637.242.4
vc-codex-high-seeded-v2-support-desk-fastapi1011836.941.9
vc-codex-high-seeded-v2-healthcare-clinic-django1001636.541.5
vc-codex-seeded-v2-marketplace-commerce-fastapi1011836.241.2
vc-claude-code-seeded-v2-legal-case-django1102035.540.7
vc-claude-code-seeded-v2-crm-saas-django1011835.740.6
vc-claude-code-seeded-v2-hr-payroll-django1001835.240.5
damn-vulnerable-graphql-application14132238.940.2
vc-claude-code-seeded-v2-logistics-dispatch-fastapi1202234.840.0
extremely-vulnerable-flask-app1102134.439.6
vc-codex-seeded-v2-support-desk-fastapi1002034.439.6
vc-kimi-code-seeded-v2-hr-payroll-django1011934.539.4
vc-claude-code-seeded-v2-support-desk-fastapi1212234.339.2
vc-kimi-code-seeded-v2-crm-saas-django921834.638.9
vc-codex-seeded-v2-legal-case-django1102233.338.5
vulnpy2715333.338.0
vc-kimi-code-seeded-v2-property-management-fastapi1032033.337.6
vc-kimi-code-seeded-v2-education-lms-django931933.337.5
vc-codex-seeded-v2-hr-payroll-django1202632.037.1
vc-codex-high-seeded-v2-legal-case-django801732.037.0
vc-claude-code-seeded-v2-healthcare-clinic-django902031.035.9
vc-claude-code-seeded-v2-property-management-fastapi1012330.335.0
vulnerable-tornado-app401030.934.4
vc-codex-high-seeded-v2-education-lms-django711829.333.6
vc-claude-code-seeded-v2-marketplace-commerce-fastapi902328.132.8
vc-claude-code-seeded-v2-education-lms-django902327.131.6
vc-codex-high-seeded-v2-hr-payroll-django711828.031.4
vc-codex-seeded-v2-crm-saas-django922526.530.7
pygoat2045825.029.1
dvpwa611724.628.7
python-insecure-app21625.028.6
vc-codex-seeded-v2-education-lms-django802624.328.5
vc-codex-seeded-v2-healthcare-clinic-django903221.925.9
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi612121.024.1
flask-xss622418.921.9
vc-codex-seeded-v2-property-management-fastapi602519.421.9
vc-claude-code-seeded-v2-fintech-lending-fastapi622419.021.3
djangoat914317.320.6
vulpy914815.818.9
damn-vulnerable-flask-application211311.112.6
§

Detection by severity

SeverityTPFPFNRecall %
Critical12502483.9
High284244838.8
Medium194168722.0
Low60787.1
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
HTTP Header Injection100100.0
Insecure Deserialization350489.7
SQL Injection650987.8
Code Injection / RFI280487.5
Open Redirect330586.8
XML External Entities311683.8
Command / OS Injection410883.7
Path Traversal2811565.1
Server-Side Request Forgery2411660.0
Cross-Site Scripting4006538.1
XPath Injection10233.3
Security Misconfiguration3407331.8
Hardcoded Credentials1705025.4
Other190066422.2
Missing Authentication / Authorization1706321.2
Broken Access Control / IDOR1606719.3
Sensitive Data Exposure801435.3
Denial of Service00430.0
§

LLM operational metrics

133,767
Avg input tokens
4,170
Avg output tokens
840,691
Avg total tokens
175s
Avg latency / repo
2.7%
JSON repair rate
149
Total runs
±11.6
F2 run-to-run σ
§

Cost

$81
Total cost
$0.55
Cost / run
$0.027
Cost / 100 LOC
131,215
Python LOC scanned
147
Successful runs

← Back to the leaderboard