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

GPT-5.6 Terra by OpenAI ↗

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

48.5
F3 (strict)
50.5
F2 (strict)
46.6%
Recall (strict)
76.4%
Precision
66/66
Repos scored
gpt-5.6-terra
Model
$39
Total cost
111s
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%
vampi89 F2 · 87%
vfapi89 F2 · 89%
insecure-web81 F2 · 78%
dsvw78 F2 · 74%
python-app71 F2 · 67%
threatbyte66 F2 · 62%
vc-codex-high-seeded-v2-hr-payroll-django65 F2 · 60%
vulnerable-flask-app64 F2 · 62%
dsvpwa64 F2 · 59%
dvblab64 F2 · 59%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi64 F2 · 60%
vc-kimi-code-seeded-v2-legal-case-django64 F2 · 62%
vc-kimi-code-seeded-v2-property-management-fastapi63 F2 · 60%
vc-claude-code-seeded-v2-support-desk-fastapi62 F2 · 59%
vulnerable-api62 F2 · 57%
vc-codex-high-seeded-v2-property-management-fastapi60 F2 · 58%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi60 F2 · 61%
extremely-vulnerable-flask-app60 F2 · 56%
vc-codex-high-seeded-v2-education-lms-django60 F2 · 56%
vulnerable-tornado-app60 F2 · 57%
vc-claude-code-seeded-v2-legal-case-django59 F2 · 55%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi59 F2 · 55%
lets-be-bad-guys59 F2 · 54%
vc-claude-code-seeded-v2-crm-saas-django57 F2 · 54%
vc-claude-code-seeded-v2-property-management-fastapi56 F2 · 52%
vc-codex-seeded-v2-legal-case-django56 F2 · 52%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi56 F2 · 52%
vc-codex-seeded-v2-marketplace-commerce-fastapi55 F2 · 52%
dvpwa54 F2 · 52%
vc-codex-seeded-v2-logistics-dispatch-fastapi54 F2 · 50%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi54 F2 · 52%
vc-kimi-code-seeded-v2-fintech-lending-fastapi54 F2 · 48%
vc-codex-high-seeded-v2-fintech-lending-fastapi53 F2 · 52%
python-insecure-app53 F2 · 50%
vc-kimi-code-seeded-v2-support-desk-fastapi52 F2 · 50%
owasp-web-playground52 F2 · 46%
vc-claude-code-seeded-v2-hr-payroll-django52 F2 · 48%
vc-claude-code-seeded-v2-fintech-lending-fastapi52 F2 · 48%
vc-kimi-code-seeded-v2-hr-payroll-django52 F2 · 48%
vc-codex-high-seeded-v2-crm-saas-django51 F2 · 48%
vc-kimi-code-seeded-v2-healthcare-clinic-django50 F2 · 47%
vc-codex-high-seeded-v2-healthcare-clinic-django49 F2 · 46%
vc-codex-seeded-v2-hr-payroll-django48 F2 · 44%
intentionally-vulnerable-python-application47 F2 · 43%
vc-codex-high-seeded-v2-support-desk-fastapi47 F2 · 43%
vc-codex-seeded-v2-support-desk-fastapi47 F2 · 43%
vulnpy46 F2 · 41%
vc-codex-seeded-v2-property-management-fastapi46 F2 · 42%
vc-kimi-code-seeded-v2-education-lms-django45 F2 · 43%
damn-vulnerable-graphql-application44 F2 · 39%
vc-codex-seeded-v2-healthcare-clinic-django43 F2 · 39%
djangoat39 F2 · 35%
vc-codex-seeded-v2-crm-saas-django39 F2 · 35%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi39 F2 · 34%
vc-claude-code-seeded-v2-healthcare-clinic-django38 F2 · 34%
vc-claude-code-seeded-v2-education-lms-django38 F2 · 34%
vc-kimi-code-seeded-v2-crm-saas-django38 F2 · 37%
pygoat37 F2 · 32%
flask-xss34 F2 · 30%
vc-codex-seeded-v2-fintech-lending-fastapi34 F2 · 30%
vc-codex-seeded-v2-education-lms-django32 F2 · 29%
vulpy31 F2 · 26%
damn-vulnerable-flask-application22 F2 · 20%
vulnerable-python-apps21 F2 · 18%
vc-codex-high-seeded-v2-legal-case-django17 F2 · 16%
RepositoryTPFPFNRecall %F2
pythonssti200100.0100.0
vampi130286.789.0
vfapi81188.988.9
insecure-web70277.881.4
dsvw201774.177.5
python-app141766.770.7
threatbyte1611061.566.1
vc-codex-high-seeded-v2-hr-payroll-django1511060.064.7
vulnerable-flask-app134861.964.4
dsvpwa1921359.463.8
dvblab131959.163.7
vc-codex-high-seeded-v2-marketplace-commerce-fastapi1531060.063.6
vc-kimi-code-seeded-v2-legal-case-django1661061.563.5
vc-kimi-code-seeded-v2-property-management-fastapi1851260.062.9
vc-claude-code-seeded-v2-support-desk-fastapi2041458.862.5
vulnerable-api81657.161.5
vc-codex-high-seeded-v2-property-management-fastapi1551157.760.5
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi19141261.360.5
extremely-vulnerable-flask-app1831456.260.4
vc-codex-high-seeded-v2-education-lms-django1431156.059.8
vulnerable-tornado-app83657.159.7
vc-claude-code-seeded-v2-legal-case-django1721454.859.4
vc-claude-code-seeded-v2-logistics-dispatch-fastapi1821554.559.2
lets-be-bad-guys1321154.258.6
vc-claude-code-seeded-v2-crm-saas-django1551353.656.8
vc-claude-code-seeded-v2-property-management-fastapi1721651.556.3
vc-codex-seeded-v2-legal-case-django1721651.556.3
vc-codex-high-seeded-v2-logistics-dispatch-fastapi1531451.756.0
vc-codex-seeded-v2-marketplace-commerce-fastapi1551451.755.1
dvpwa1261152.254.5
vc-codex-seeded-v2-logistics-dispatch-fastapi1531550.054.3
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi1481351.853.8
vc-kimi-code-seeded-v2-fintech-lending-fastapi1611748.553.7
vc-codex-high-seeded-v2-fintech-lending-fastapi15101451.753.2
python-insecure-app42450.052.6
vc-kimi-code-seeded-v2-support-desk-fastapi1481450.052.2
owasp-web-playground1301546.452.0
vc-claude-code-seeded-v2-hr-payroll-django1351448.151.6
vc-claude-code-seeded-v2-fintech-lending-fastapi1461548.351.5
vc-kimi-code-seeded-v2-hr-payroll-django1461548.351.5
vc-codex-high-seeded-v2-crm-saas-django1251348.051.3
vc-kimi-code-seeded-v2-healthcare-clinic-django1451646.750.4
vc-codex-high-seeded-v2-healthcare-clinic-django1261446.249.2
vc-codex-seeded-v2-hr-payroll-django1732243.648.3
intentionally-vulnerable-python-application31442.946.9
vc-codex-high-seeded-v2-support-desk-fastapi1241642.946.9
vc-codex-seeded-v2-support-desk-fastapi1361743.346.8
vulnpy3374741.245.8
vc-codex-seeded-v2-property-management-fastapi1351841.945.8
vc-kimi-code-seeded-v2-education-lms-django12101642.944.8
damn-vulnerable-graphql-application1422238.943.8
vc-codex-seeded-v2-healthcare-clinic-django1682539.042.6
djangoat1853434.639.0
vc-codex-seeded-v2-crm-saas-django1262235.339.0
vc-claude-code-seeded-v2-marketplace-commerce-fastapi1132134.438.7
vc-claude-code-seeded-v2-healthcare-clinic-django1041934.538.5
vc-claude-code-seeded-v2-education-lms-django1152134.438.2
vc-kimi-code-seeded-v2-crm-saas-django10131737.038.2
pygoat2545332.036.7
flask-xss922130.034.4
vc-codex-seeded-v2-fintech-lending-fastapi1112629.734.4
vc-codex-seeded-v2-education-lms-django1052528.632.3
vulpy1524226.330.6
damn-vulnerable-flask-application361220.021.7
vulnerable-python-apps441818.220.8
vc-codex-high-seeded-v2-legal-case-django4142116.016.9
§

Detection by severity

SeverityTPFPFNRecall %
Critical13701888.4
High406034654.0
Medium315159534.6
Low2805832.6
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
XPath Injection400100.0
Open Redirect390197.5
Insecure Deserialization370392.5
Command / OS Injection450590.0
XML External Entities340489.5
SQL Injection6701185.9
Code Injection / RFI280682.4
Path Traversal3001468.2
Server-Side Request Forgery2711465.9
Cross-Site Scripting6504559.1
Hardcoded Credentials3803055.9
Security Misconfiguration6005253.6
HTTP Header Injection10150.0
Sensitive Data Exposure7707849.7
Missing Authentication / Authorization3404941.0
Denial of Service1802640.9
Broken Access Control / IDOR3105237.3
Other251062628.6
§

LLM operational metrics

384,521
Avg input tokens
5,219
Avg output tokens
391,543
Avg total tokens
111s
Avg latency / repo
0.0%
JSON repair rate
66
Total runs
§

Cost

$39
Total cost
$0.60
Cost / run
$0.029
Cost / 100 LOC
133,782
Python LOC scanned
66
Successful runs

← Back to the leaderboard