You are viewing an archived release — RealVuln v3.1.0. View the latest benchmark →
realvuln v3.1
Dashboard Methodology Dataset Findings Roadmap GitHub ↗
Scanner deep-dive

GPT-5.6 Sol by OpenAI ↗

General-Purpose LLM · codex-cli · scored on 140/140 repositories. Strict scoring (unfinished repos counted as misses).

Methodology note
Full coverage; subscription-metered. Runs through the Codex CLI authenticated against a ChatGPT subscription session rather than a metered OpenAI API key, at model_reasoning_effort=high on both languages. The cost shown is computed from Codex's reported token usage at OpenAI's published API rate for this model ($4.00/$20.00 per 1M input/output tokens, short context) -- an accurate estimate of what the run would cost if billed, not money actually charged on a subscription session.

The Python figure was re-run. Our Codex runner had no reasoning-effort control at all until the TS/JS work in this release, so the original Python campaign ran at whatever Codex's ambient default was (unrecorded) rather than high. Re-running all 66 Python repositories at high on 2026-09-05 moved F3 from 53.9 to 77.8 (recall 48.3% to 78.7%, precision 78.5% to 70.6%) — confirming the mismatch, not the corpus, explained most of the earlier Python/TS-JS gap. The run was interrupted twice by the Codex/ChatGPT subscription's usage limit and resumed after each reset; every repository is now scored at the same effort level. The 74 TypeScript / JS repositories were scanned once each on 2026-09-04 with the same TS/JS prompt as the DeepSeek runs (prompt hash sha256:45a1200d61e6); all 74 validated first time.
74.7
F3 (strict)
72.6
F2 (strict)
76.9%
Recall (strict)
59.3%
Precision
140/140
Repos scored
gpt-5.6-sol
Model
$560
Total cost
569s
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)
insecure-web100 F2 · 100%
lets-be-bad-guys100 F2 · 100%
nextjs-vulnerable-app100 F2 · 100%
pythonssti100 F2 · 100%
react-test-bench100 F2 · 100%
vampi100 F2 · 100%
vfapi100 F2 · 100%
vuln-node-express100 F2 · 100%
vc-claude-code-seeded-v2-education-lms-django100 F2 · 100%
vc-claude-code-seeded-v2-property-management-fastapi100 F2 · 100%
vc-claude-code-seeded-v3-marketplace-commerce-express100 F2 · 100%
vc-codex-high-seeded-v2-crm-saas-django100 F2 · 100%
vc-codex-high-seeded-v3-support-desk-nestjs-angular100 F2 · 100%
vc-deepseek-v4-pro-seeded-v3-crm-saas-nestjs-angular100 F2 · 100%
vc-kimi-code-seeded-v2-healthcare-clinic-django100 F2 · 100%
vc-codex-seeded-v2-healthcare-clinic-django100 F2 · 100%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi99 F2 · 100%
vc-codex-high-seeded-v2-fintech-lending-fastapi99 F2 · 100%
vc-codex-seeded-v2-hr-payroll-django98 F2 · 100%
vc-claude-code-seeded-v3-hr-payroll-remix97 F2 · 97%
vc-claude-code-seeded-v2-crm-saas-django97 F2 · 100%
vc-codex-high-seeded-v3-fintech-lending-express97 F2 · 100%
vc-claude-code-seeded-v2-legal-case-django97 F2 · 100%
vc-codex-seeded-v2-property-management-fastapi96 F2 · 100%
vc-codex-seeded-v2-legal-case-django96 F2 · 100%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi95 F2 · 100%
vc-codex-high-seeded-v2-support-desk-fastapi95 F2 · 100%
vc-codex-seeded-v2-logistics-dispatch-fastapi95 F2 · 100%
vc-kimi-code-seeded-v3-healthcare-clinic-nextjs94 F2 · 94%
vc-codex-high-seeded-v3-healthcare-clinic-nextjs94 F2 · 100%
vc-claude-code-seeded-v3-support-desk-nestjs-angular94 F2 · 100%
vc-claude-code-seeded-v2-healthcare-clinic-django94 F2 · 100%
vuln-node-express-swagger93 F2 · 98%
vc-codex-seeded-v2-education-lms-django93 F2 · 97%
vc-codex-high-seeded-v3-marketplace-commerce-express93 F2 · 100%
vc-kimi-code-seeded-v2-support-desk-fastapi92 F2 · 100%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi92 F2 · 100%
vc-kimi-code-seeded-v2-hr-payroll-django91 F2 · 100%
extremely-vulnerable-flask-app90 F2 · 94%
vc-deepseek-v4-pro-seeded-v3-legal-case-remix89 F2 · 96%
vc-codex-high-seeded-v3-property-management-fastify-vue89 F2 · 98%
vc-codex-high-seeded-v3-crm-saas-nestjs-angular88 F2 · 95%
vc-kimi-code-seeded-v2-crm-saas-django88 F2 · 100%
vc-kimi-code-seeded-v3-education-lms-nextjs88 F2 · 100%
vc-kimi-code-seeded-v3-logistics-dispatch-fastify-vue87 F2 · 98%
vc-claude-code-seeded-v3-property-management-fastify-vue87 F2 · 97%
dvws-node86 F2 · 88%
python-insecure-app85 F2 · 88%
vulnerable-app-angular85 F2 · 100%
ivna85 F2 · 95%
vc-kimi-code-seeded-v2-legal-case-django84 F2 · 96%
vc-kimi-code-seeded-v3-property-management-fastify-vue84 F2 · 97%
vc-claude-code-seeded-v3-crm-saas-nestjs-angular83 F2 · 86%
vc-deepseek-v4-flash-seeded-v3-hr-payroll-remix83 F2 · 100%
juice-shop-goof83 F2 · 88%
dvna82 F2 · 88%
vc-deepseek-v4-flash-seeded-v3-crm-saas-nestjs-angular81 F2 · 91%
vc-kimi-code-seeded-v3-support-desk-nestjs-angular81 F2 · 97%
dvblab80 F2 · 86%
vc-codex-seeded-v2-fintech-lending-fastapi80 F2 · 78%
vulnnodeapp80 F2 · 86%
damn-vulnerable-graphql-application79 F2 · 81%
vc-deepseek-v4-flash-seeded-v3-marketplace-commerce-express79 F2 · 90%
threatbyte79 F2 · 81%
vc-deepseek-v4-flash-seeded-v3-logistics-dispatch-fastify-vue79 F2 · 96%
vc-claude-code-seeded-v3-education-lms-nextjs79 F2 · 87%
vc-codex-high-seeded-v3-hr-payroll-remix78 F2 · 88%
dsvw77 F2 · 74%
react-security76 F2 · 100%
vc-codex-high-seeded-v2-hr-payroll-django76 F2 · 80%
python-app76 F2 · 76%
vc-claude-code-seeded-v2-support-desk-fastapi74 F2 · 74%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi73 F2 · 76%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi73 F2 · 84%
vc-kimi-code-seeded-v2-property-management-fastapi73 F2 · 87%
vc-claude-code-seeded-v2-fintech-lending-fastapi72 F2 · 76%
intentionally-vulnerable-python-application71 F2 · 71%
nodegoat71 F2 · 75%
vc-deepseek-v4-flash-seeded-v3-property-management-fastify-vue71 F2 · 92%
vulnpy71 F2 · 69%
vc-codex-high-seeded-v2-property-management-fastapi71 F2 · 77%
vc-codex-seeded-v2-marketplace-commerce-fastapi71 F2 · 72%
dsvpwa71 F2 · 72%
node-api-goat69 F2 · 71%
xvna69 F2 · 83%
vc-kimi-code-seeded-v2-education-lms-django69 F2 · 79%
vc-deepseek-v4-pro-seeded-v3-healthcare-clinic-nextjs69 F2 · 81%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi69 F2 · 78%
vulnerable-tornado-app68 F2 · 71%
owasp-web-playground66 F2 · 64%
djangoat65 F2 · 67%
vc-codex-high-seeded-v2-education-lms-django65 F2 · 64%
vc-codex-seeded-v2-support-desk-fastapi65 F2 · 63%
vc-claude-code-seeded-v3-legal-case-remix64 F2 · 71%
nodejs-goof60 F2 · 71%
vc-claude-code-seeded-v3-logistics-dispatch-fastify-vue60 F2 · 63%
vc-codex-seeded-v2-crm-saas-django60 F2 · 59%
vulnerable-flask-app59 F2 · 57%
vulnerable-nodejs59 F2 · 63%
vc-kimi-code-seeded-v3-fintech-lending-express59 F2 · 62%
vc-kimi-code-seeded-v2-fintech-lending-fastapi58 F2 · 58%
vulnerable-node58 F2 · 62%
vc-deepseek-v4-flash-seeded-v3-education-lms-nextjs57 F2 · 61%
vc-kimi-code-seeded-v3-marketplace-commerce-express57 F2 · 60%
vc-deepseek-v4-flash-seeded-v3-legal-case-remix56 F2 · 64%
pygoat56 F2 · 55%
vc-deepseek-v4-flash-seeded-v3-fintech-lending-express56 F2 · 68%
vc-kimi-code-seeded-v3-legal-case-remix54 F2 · 56%
juice-shop54 F2 · 56%
vc-codex-high-seeded-v3-logistics-dispatch-fastify-vue53 F2 · 56%
vc-deepseek-v4-flash-seeded-v3-healthcare-clinic-nextjs53 F2 · 62%
vulnerable-rest-api-owasp-202353 F2 · 67%
dvpwa51 F2 · 48%
vc-claude-code-seeded-v3-fintech-lending-express50 F2 · 55%
damn-vulnerable-flask-application50 F2 · 50%
flask-xss50 F2 · 47%
vc-codex-high-seeded-v2-healthcare-clinic-django49 F2 · 50%
vc-codex-high-seeded-v3-legal-case-remix49 F2 · 49%
vc-kimi-code-seeded-v3-hr-payroll-remix48 F2 · 53%
vc-claude-code-seeded-v3-healthcare-clinic-nextjs48 F2 · 51%
vulnerable-api47 F2 · 43%
vc-deepseek-v4-pro-seeded-v3-support-desk-nestjs-angular46 F2 · 63%
reactvulna46 F2 · 100%
vc-codex-high-seeded-v3-education-lms-nextjs46 F2 · 46%
vc-deepseek-v4-pro-seeded-v3-logistics-dispatch-fastify-vue44 F2 · 57%
vulnerable-react-fatih44 F2 · 57%
vc-kimi-code-seeded-v3-crm-saas-nestjs-angular43 F2 · 48%
vc-deepseek-v4-pro-seeded-v3-education-lms-nextjs42 F2 · 48%
vc-deepseek-v4-pro-seeded-v3-property-management-fastify-vue41 F2 · 53%
oss-oopssec-store40 F2 · 42%
vc-claude-code-seeded-v2-hr-payroll-django40 F2 · 37%
vc-deepseek-v4-flash-seeded-v3-support-desk-nestjs-angular36 F2 · 38%
vulpy36 F2 · 33%
vc-codex-high-seeded-v2-legal-case-django34 F2 · 36%
vulnerable-python-apps33 F2 · 32%
vc-deepseek-v4-pro-seeded-v3-hr-payroll-remix32 F2 · 35%
vc-deepseek-v4-pro-seeded-v3-marketplace-commerce-express29 F2 · 31%
vc-deepseek-v4-pro-seeded-v3-fintech-lending-express28 F2 · 30%
simply-vulnerable-react25 F2 · 100%
ninjasworkout21 F2 · 23%
RepositoryTPFPFNRecall %F2
insecure-web900100.0100.0
lets-be-bad-guys2400100.0100.0
nextjs-vulnerable-app100100.0100.0
pythonssti200100.0100.0
react-test-bench100100.0100.0
vampi1500100.0100.0
vfapi900100.0100.0
vuln-node-express500100.0100.0
vc-claude-code-seeded-v2-education-lms-django3200100.0100.0
vc-claude-code-seeded-v2-property-management-fastapi3300100.0100.0
vc-claude-code-seeded-v3-marketplace-commerce-express4000100.0100.0
vc-codex-high-seeded-v2-crm-saas-django2500100.0100.0
vc-codex-high-seeded-v3-support-desk-nestjs-angular3500100.0100.0
vc-deepseek-v4-pro-seeded-v3-crm-saas-nestjs-angular3000100.0100.0
vc-kimi-code-seeded-v2-healthcare-clinic-django3000100.0100.0
vc-codex-seeded-v2-healthcare-clinic-django4110100.099.5
vc-codex-high-seeded-v2-marketplace-commerce-fastapi2510100.099.2
vc-codex-high-seeded-v2-fintech-lending-fastapi2920100.098.6
vc-codex-seeded-v2-hr-payroll-django3930100.098.5
vc-claude-code-seeded-v3-hr-payroll-remix361197.397.3
vc-claude-code-seeded-v2-crm-saas-django2840100.097.2
vc-codex-high-seeded-v3-fintech-lending-express3960100.097.0
vc-claude-code-seeded-v2-legal-case-django3150100.096.9
vc-codex-seeded-v2-property-management-fastapi3160100.096.3
vc-codex-seeded-v2-legal-case-django3370100.095.9
vc-claude-code-seeded-v2-marketplace-commerce-fastapi3280100.095.2
vc-codex-high-seeded-v2-support-desk-fastapi2870100.095.2
vc-codex-seeded-v2-logistics-dispatch-fastapi3080100.094.9
vc-kimi-code-seeded-v3-healthcare-clinic-nextjs342294.494.4
vc-codex-high-seeded-v3-healthcare-clinic-nextjs42140100.093.8
vc-claude-code-seeded-v3-support-desk-nestjs-angular41140100.093.6
vc-claude-code-seeded-v2-healthcare-clinic-django29100100.093.5
vuln-node-express-swagger4813198.093.4
vc-codex-seeded-v2-education-lms-django349197.192.9
vc-codex-high-seeded-v3-marketplace-commerce-express44170100.092.8
vc-kimi-code-seeded-v2-support-desk-fastapi28120100.092.1
vc-codex-high-seeded-v2-logistics-dispatch-fastapi29130100.091.8
vc-kimi-code-seeded-v2-hr-payroll-django29150100.090.6
extremely-vulnerable-flask-app308293.890.4
vc-deepseek-v4-pro-seeded-v3-legal-case-remix2411196.088.9
vc-codex-high-seeded-v3-property-management-fastify-vue4122197.688.7
vc-codex-high-seeded-v3-crm-saas-nestjs-angular3515294.688.4
vc-kimi-code-seeded-v2-crm-saas-django27180100.088.2
vc-kimi-code-seeded-v3-education-lms-nextjs46330100.087.5
vc-kimi-code-seeded-v3-logistics-dispatch-fastify-vue4327197.787.4
vc-claude-code-seeded-v3-property-management-fastify-vue3119196.987.1
dvws-node6817988.386.5
python-insecure-app72187.585.4
vulnerable-app-angular870100.085.1
ivna1812194.784.9
vc-kimi-code-seeded-v2-legal-case-django2519196.284.5
vc-kimi-code-seeded-v3-property-management-fastify-vue3126196.983.8
vc-claude-code-seeded-v3-crm-saas-nestjs-angular4214785.783.3
vc-deepseek-v4-flash-seeded-v3-hr-payroll-remix18180100.083.3
juice-shop-goof4522688.283.0
dvna158288.282.4
vc-deepseek-v4-flash-seeded-v3-crm-saas-nestjs-angular2015290.981.3
vc-kimi-code-seeded-v3-support-desk-nestjs-angular3133196.980.7
dvblab1911386.480.5
vc-codex-seeded-v2-fintech-lending-fastapi294878.480.1
vulnnodeapp2516486.279.6
damn-vulnerable-graphql-application2910780.679.2
vc-deepseek-v4-flash-seeded-v3-marketplace-commerce-express1917290.579.2
threatbyte218580.878.9
vc-deepseek-v4-flash-seeded-v3-logistics-dispatch-fastify-vue2732196.478.9
vc-claude-code-seeded-v3-education-lms-nextjs3325586.878.6
vc-codex-high-seeded-v3-hr-payroll-remix3732588.178.1
dsvw202774.176.9
react-security7110100.076.1
vc-codex-high-seeded-v2-hr-payroll-django2012580.075.8
python-app166576.275.5
vc-claude-code-seeded-v2-support-desk-fastapi259973.573.5
vc-claude-code-seeded-v2-logistics-dispatch-fastapi2515875.872.7
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi2629583.972.6
vc-kimi-code-seeded-v2-property-management-fastapi2633486.772.6
vc-claude-code-seeded-v2-fintech-lending-fastapi2215775.971.9
intentionally-vulnerable-python-application52271.471.4
nodegoat2114775.071.4
vc-deepseek-v4-flash-seeded-v3-property-management-fastify-vue2338292.071.4
vulnpy55122568.871.1
vc-codex-high-seeded-v2-property-management-fastapi2017676.970.9
vc-codex-seeded-v2-marketplace-commerce-fastapi2111872.470.9
dsvpwa2312971.970.6
node-api-goat53271.469.4
xvna1014283.369.4
vc-kimi-code-seeded-v2-education-lms-django2225678.669.2
vc-deepseek-v4-pro-seeded-v3-healthcare-clinic-nextjs2128580.868.6
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi2124677.868.6
vulnerable-tornado-app108471.467.6
owasp-web-playground1871064.365.7
djangoat35251767.365.3
vc-codex-high-seeded-v2-education-lms-django167964.065.0
vc-codex-seeded-v2-support-desk-fastapi1981163.364.6
vc-claude-code-seeded-v3-legal-case-remix2023871.464.5
nodejs-goof1220570.660.0
vc-claude-code-seeded-v3-logistics-dispatch-fastify-vue32311962.759.9
vc-codex-seeded-v2-crm-saas-django20121458.859.5
vulnerable-flask-app126957.158.8
vulnerable-nodejs1214763.258.8
vc-kimi-code-seeded-v3-fintech-lending-express26281661.958.6
vc-kimi-code-seeded-v2-fintech-lending-fastapi19131457.657.9
vulnerable-node1316861.957.5
vc-deepseek-v4-flash-seeded-v3-education-lms-nextjs17191160.757.4
vc-kimi-code-seeded-v3-marketplace-commerce-express26291760.557.3
vc-deepseek-v4-flash-seeded-v3-legal-case-remix1422863.656.5
pygoat43283555.156.1
vc-deepseek-v4-flash-seeded-v3-fintech-lending-express1531768.256.0
vc-kimi-code-seeded-v3-legal-case-remix23251856.154.2
juice-shop45473655.654.1
vc-codex-high-seeded-v3-logistics-dispatch-fastify-vue25292055.653.4
vc-deepseek-v4-flash-seeded-v3-healthcare-clinic-nextjs1531962.552.8
vulnerable-rest-api-owasp-20231025566.752.6
dvpwa1151247.850.9
vc-claude-code-seeded-v3-fintech-lending-express22361855.050.5
damn-vulnerable-flask-application77750.050.0
flask-xss1461646.750.0
vc-codex-high-seeded-v2-healthcare-clinic-django13161350.048.9
vc-codex-high-seeded-v3-legal-case-remix23252448.948.7
vc-kimi-code-seeded-v3-hr-payroll-remix19351752.848.0
vc-claude-code-seeded-v3-healthcare-clinic-nextjs22372151.247.6
vulnerable-api62842.946.9
vc-deepseek-v4-pro-seeded-v3-support-desk-nestjs-angular1242763.246.2
reactvulna160100.045.5
vc-codex-high-seeded-v3-education-lms-nextjs22282645.845.5
vc-deepseek-v4-pro-seeded-v3-logistics-dispatch-fastify-vue17551356.744.3
vulnerable-react-fatih414357.143.5
vc-kimi-code-seeded-v3-crm-saas-nestjs-angular19442147.542.6
vc-deepseek-v4-pro-seeded-v3-education-lms-nextjs13341448.141.9
vc-deepseek-v4-pro-seeded-v3-property-management-fastify-vue1037952.640.7
oss-oopssec-store17342342.540.3
vc-claude-code-seeded-v2-hr-payroll-django1061737.040.3
vc-deepseek-v4-flash-seeded-v3-support-desk-nestjs-angular9201537.536.0
vulpy19183833.335.8
vc-codex-high-seeded-v2-legal-case-django9251636.033.6
vulnerable-python-apps7101531.833.3
vc-deepseek-v4-pro-seeded-v3-hr-payroll-remix9271734.632.1
vc-deepseek-v4-pro-seeded-v3-marketplace-commerce-express8281830.828.6
vc-deepseek-v4-pro-seeded-v3-fintech-lending-express8271929.628.0
simply-vulnerable-react1150100.025.0
ninjasworkout5281722.720.7
§

Detection by severity

SeverityTPFPFNRecall %
Critical14501391.8
High2196165277.1
Medium737222976.3
Low10506163.3
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
XPath Injection1700100.0
Open Redirect850396.6
Insecure Deserialization450393.8
Path Traversal960892.3
XML External Entities590592.2
Command / OS Injection12401291.2
SQL Injection13501987.7
Code Injection / RFI7001087.5
Cross-Site Scripting16504180.1
Server-Side Request Forgery7411979.6
Security Misconfiguration16104378.9
Broken Access Control / IDOR18314978.9
Denial of Service6801978.2
Missing Authentication / Authorization12804574.0
Other1386049973.5
Sensitive Data Exposure248010171.1
Hardcoded Credentials13817863.9
HTTP Header Injection10150.0
§

LLM operational metrics

2,539,446
Avg input tokens
26,597
Avg output tokens
2,580,604
Avg total tokens
569s
Avg latency / repo
0.0%
JSON repair rate
140
Total runs
§

Cost

$560
Total cost
$4.00
Cost / run
$0.076
Cost / 100 LOC
741,034
Lines of code scanned
140
Successful runs

← Back to the leaderboard