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

GPT-5.6 Sol by OpenAI ↗

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

53.8
F3 (strict)
55.5
F2 (strict)
52.2%
Recall (strict)
74.4%
Precision
66/66
Repos scored
gpt-5.6-sol
Model
$86
Total cost
152s
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%
insecure-web89 F2 · 89%
vfapi89 F2 · 89%
pygoat86 F2 · 85%
vampi75 F2 · 73%
dsvw75 F2 · 70%
python-app71 F2 · 67%
vc-kimi-code-seeded-v2-legal-case-django69 F2 · 69%
vc-kimi-code-seeded-v2-support-desk-fastapi67 F2 · 68%
vc-codex-high-seeded-v2-education-lms-django67 F2 · 64%
vc-kimi-code-seeded-v2-fintech-lending-fastapi64 F2 · 64%
vc-codex-high-seeded-v2-hr-payroll-django64 F2 · 60%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi63 F2 · 62%
dvblab62 F2 · 59%
intentionally-vulnerable-python-application62 F2 · 57%
vulnerable-api62 F2 · 57%
vc-kimi-code-seeded-v2-education-lms-django62 F2 · 61%
vc-claude-code-seeded-v2-legal-case-django61 F2 · 58%
vc-kimi-code-seeded-v2-healthcare-clinic-django61 F2 · 60%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi61 F2 · 59%
threatbyte60 F2 · 58%
vc-claude-code-seeded-v2-support-desk-fastapi59 F2 · 56%
vc-claude-code-seeded-v2-crm-saas-django59 F2 · 57%
dsvpwa59 F2 · 56%
lets-be-bad-guys59 F2 · 54%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi59 F2 · 56%
extremely-vulnerable-flask-app59 F2 · 53%
vc-codex-seeded-v2-logistics-dispatch-fastapi58 F2 · 53%
vc-codex-seeded-v2-marketplace-commerce-fastapi58 F2 · 55%
vc-codex-high-seeded-v2-crm-saas-django58 F2 · 56%
vc-codex-seeded-v2-hr-payroll-django58 F2 · 54%
vc-claude-code-seeded-v2-fintech-lending-fastapi58 F2 · 55%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi58 F2 · 61%
owasp-web-playground57 F2 · 54%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi57 F2 · 55%
vc-codex-seeded-v2-healthcare-clinic-django57 F2 · 54%
damn-vulnerable-graphql-application57 F2 · 53%
vc-claude-code-seeded-v2-education-lms-django57 F2 · 53%
dvpwa56 F2 · 52%
vc-claude-code-seeded-v2-property-management-fastapi56 F2 · 52%
vc-codex-seeded-v2-legal-case-django56 F2 · 52%
vc-codex-seeded-v2-support-desk-fastapi54 F2 · 50%
vc-kimi-code-seeded-v2-property-management-fastapi52 F2 · 50%
vc-codex-seeded-v2-property-management-fastapi52 F2 · 48%
vc-claude-code-seeded-v2-hr-payroll-django52 F2 · 48%
vulnpy52 F2 · 48%
vulnerable-flask-app51 F2 · 48%
vc-codex-seeded-v2-crm-saas-django50 F2 · 47%
vc-codex-high-seeded-v2-property-management-fastapi49 F2 · 46%
vc-codex-high-seeded-v2-fintech-lending-fastapi48 F2 · 45%
vc-kimi-code-seeded-v2-crm-saas-django48 F2 · 48%
vc-kimi-code-seeded-v2-hr-payroll-django47 F2 · 45%
vc-codex-high-seeded-v2-support-desk-fastapi47 F2 · 43%
vulnerable-tornado-app46 F2 · 43%
vc-codex-high-seeded-v2-healthcare-clinic-django46 F2 · 42%
vc-codex-seeded-v2-education-lms-django44 F2 · 40%
vc-claude-code-seeded-v2-healthcare-clinic-django42 F2 · 38%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi42 F2 · 38%
python-insecure-app42 F2 · 38%
flask-xss38 F2 · 33%
djangoat38 F2 · 35%
vc-codex-seeded-v2-fintech-lending-fastapi37 F2 · 32%
vulpy34 F2 · 30%
vulnerable-python-apps31 F2 · 27%
vc-codex-high-seeded-v2-legal-case-django31 F2 · 32%
damn-vulnerable-flask-application8 F2 · 7%
RepositoryTPFPFNRecall %F2
pythonssti200100.0100.0
insecure-web81188.988.9
vfapi81188.988.9
pygoat6641284.686.4
vampi112473.375.3
dsvw190870.474.8
python-app140766.771.4
vc-kimi-code-seeded-v2-legal-case-django188869.269.2
vc-kimi-code-seeded-v2-support-desk-fastapi1910967.967.4
vc-codex-high-seeded-v2-education-lms-django164964.066.7
vc-kimi-code-seeded-v2-fintech-lending-fastapi21101263.664.4
vc-codex-high-seeded-v2-hr-payroll-django1531060.063.6
vc-codex-high-seeded-v2-logistics-dispatch-fastapi1891162.162.9
dvblab133959.162.5
intentionally-vulnerable-python-application40357.162.5
vulnerable-api80657.162.5
vc-kimi-code-seeded-v2-education-lms-django1791160.761.6
vc-claude-code-seeded-v2-legal-case-django1851358.161.2
vc-kimi-code-seeded-v2-healthcare-clinic-django1891260.061.2
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi1671159.361.1
threatbyte1551157.760.5
vc-claude-code-seeded-v2-support-desk-fastapi1951555.959.4
vc-claude-code-seeded-v2-crm-saas-django1671257.159.3
dsvpwa1861456.259.2
lets-be-bad-guys1311154.259.1
vc-codex-high-seeded-v2-marketplace-commerce-fastapi1451156.058.8
extremely-vulnerable-flask-app1701553.158.6
vc-codex-seeded-v2-logistics-dispatch-fastapi1611453.358.4
vc-codex-seeded-v2-marketplace-commerce-fastapi1651355.258.4
vc-codex-high-seeded-v2-crm-saas-django1461156.058.3
vc-codex-seeded-v2-hr-payroll-django2131853.858.3
vc-claude-code-seeded-v2-fintech-lending-fastapi1661355.258.0
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi19221261.357.6
owasp-web-playground1541353.657.3
vc-claude-code-seeded-v2-logistics-dispatch-fastapi1871554.557.3
vc-codex-seeded-v2-healthcare-clinic-django2261953.757.3
damn-vulnerable-graphql-application1931752.857.2
vc-claude-code-seeded-v2-education-lms-django1741553.157.0
dvpwa1241152.255.6
vc-claude-code-seeded-v2-property-management-fastapi1741651.555.6
vc-codex-seeded-v2-legal-case-django1741651.555.6
vc-codex-seeded-v2-support-desk-fastapi1551550.053.6
vc-kimi-code-seeded-v2-property-management-fastapi1581550.052.4
vc-codex-seeded-v2-property-management-fastapi1551648.452.1
vc-claude-code-seeded-v2-hr-payroll-django1341448.152.0
vulnpy3884247.551.9
vulnerable-flask-app1041147.651.0
vc-codex-seeded-v2-crm-saas-django1681847.150.0
vc-codex-high-seeded-v2-property-management-fastapi1271446.248.8
vc-codex-high-seeded-v2-fintech-lending-fastapi1351644.848.5
vc-kimi-code-seeded-v2-crm-saas-django13151448.147.8
vc-kimi-code-seeded-v2-hr-payroll-django1381644.847.4
vc-codex-high-seeded-v2-support-desk-fastapi1241642.946.9
vulnerable-tornado-app63842.946.2
vc-codex-high-seeded-v2-healthcare-clinic-django1141542.346.2
vc-codex-seeded-v2-education-lms-django1452140.044.0
vc-claude-code-seeded-v2-healthcare-clinic-django1131837.942.3
vc-claude-code-seeded-v2-marketplace-commerce-fastapi1222037.542.3
python-insecure-app31537.541.7
flask-xss1012033.338.2
djangoat18143434.637.5
vc-codex-seeded-v2-fintech-lending-fastapi1232532.436.8
vulpy1754029.834.0
vulnerable-python-apps621627.331.2
vc-codex-high-seeded-v2-legal-case-django8201732.031.2
damn-vulnerable-flask-application16146.77.5
§

Detection by severity

SeverityTPFPFNRecall %
Critical13801789.0
High442031058.8
Medium383352742.1
Low3105536.0
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
HTTP Header Injection200100.0
Open Redirect390197.5
Insecure Deserialization370392.5
Command / OS Injection450590.0
XML External Entities330586.8
SQL Injection6701185.9
Code Injection / RFI290585.3
Path Traversal370784.1
Cross-Site Scripting7503568.2
Server-Side Request Forgery2721465.9
Broken Access Control / IDOR4703656.6
Security Misconfiguration6304956.2
Hardcoded Credentials3813055.9
Sensitive Data Exposure8207352.9
Missing Authentication / Authorization4204150.6
Other316056136.0
Denial of Service1403031.8
XPath Injection10325.0
§

LLM operational metrics

451,748
Avg input tokens
6,800
Avg output tokens
460,266
Avg total tokens
152s
Avg latency / repo
0.0%
JSON repair rate
66
Total runs
§

Cost

$86
Total cost
$1.30
Cost / run
$0.064
Cost / 100 LOC
133,782
Python LOC scanned
66
Successful runs

← Back to the leaderboard