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

Daybreak Blue 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. gpt-daybreak-blue-latest is an OpenAI Codex CLI alias that, per OpenAI's own model docs, currently resolves to the same underlying weights as gpt-5.6-sol — the difference is the Daybreak program's defensive-cybersecurity system instructions and safety calibration, not a different model. Despite that, at matched high reasoning effort it scores well above plain Sol on both languages (Python F3 80.0 vs 77.8, TS/JS F3 79.2 vs 72.1, Overall 79.5 vs 74.7) and on a same-repo pilot the gap was starker still (F3 88.3 vs 57.1). Whatever the Daybreak instructions change, it changes scanning behavior substantially. OpenAI's official Daybreak pricing card lists this alias at the identical rate as gpt-5.6-sol ($4.00/$20.00 per 1M input/output, short context), which is what the cost figure here uses -- computed from Codex's reported token usage, not billed spend, same convention as Sol. All 74 TypeScript / JS repositories were scanned on 2026-09-04 with the TS/JS prompt (hash sha256:45a1200d61e6); all 66 Python repositories were scanned on 2026-09-05 with the standard prompt. All 140 runs validated first time.
79.5
F3 (strict)
77.4
F2 (strict)
81.8%
Recall (strict)
64.0%
Precision
140/140
Repos scored
gpt-daybreak-blue-latest
Model
$548
Total cost
347s
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-application100 F2 · 100%
juice-shop100 F2 · 100%
lets-be-bad-guys100 F2 · 100%
pythonssti100 F2 · 100%
react-test-bench100 F2 · 100%
simply-vulnerable-react100 F2 · 100%
vampi100 F2 · 100%
vfapi100 F2 · 100%
vc-claude-code-seeded-v2-education-lms-django100 F2 · 100%
vc-claude-code-seeded-v2-legal-case-django100 F2 · 100%
vc-claude-code-seeded-v3-crm-saas-nestjs-angular100 F2 · 100%
vc-codex-high-seeded-v2-fintech-lending-fastapi100 F2 · 100%
vc-codex-high-seeded-v3-property-management-fastify-vue100 F2 · 100%
vc-codex-seeded-v2-education-lms-django100 F2 · 100%
vc-codex-seeded-v2-healthcare-clinic-django100 F2 · 100%
vc-codex-seeded-v2-support-desk-fastapi100 F2 · 100%
vc-deepseek-v4-pro-seeded-v3-property-management-fastify-vue100 F2 · 100%
vc-kimi-code-seeded-v2-healthcare-clinic-django100 F2 · 100%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi100 F2 · 100%
vc-kimi-code-seeded-v3-crm-saas-nestjs-angular100 F2 · 100%
vc-kimi-code-seeded-v3-hr-payroll-remix100 F2 · 100%
vc-claude-code-seeded-v3-hr-payroll-remix100 F2 · 100%
vc-claude-code-seeded-v2-support-desk-fastapi99 F2 · 100%
vc-codex-seeded-v2-crm-saas-django99 F2 · 100%
vc-claude-code-seeded-v2-hr-payroll-django98 F2 · 100%
vc-claude-code-seeded-v2-property-management-fastapi98 F2 · 100%
insecure-web98 F2 · 100%
vc-codex-seeded-v2-legal-case-django98 F2 · 100%
vc-claude-code-seeded-v2-crm-saas-django97 F2 · 100%
vc-codex-high-seeded-v2-healthcare-clinic-django97 F2 · 100%
vc-claude-code-seeded-v3-marketplace-commerce-express96 F2 · 100%
dvws-node96 F2 · 100%
dsvw96 F2 · 96%
vc-codex-seeded-v2-hr-payroll-django95 F2 · 95%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi95 F2 · 100%
vc-codex-high-seeded-v2-property-management-fastapi94 F2 · 100%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi94 F2 · 100%
vc-kimi-code-seeded-v2-crm-saas-django94 F2 · 100%
vc-claude-code-seeded-v2-healthcare-clinic-django94 F2 · 100%
vc-deepseek-v4-flash-seeded-v3-education-lms-nextjs93 F2 · 100%
vc-claude-code-seeded-v2-fintech-lending-fastapi92 F2 · 100%
node-api-goat92 F2 · 100%
vc-codex-seeded-v2-logistics-dispatch-fastapi92 F2 · 100%
vc-kimi-code-seeded-v2-education-lms-django92 F2 · 100%
ivna91 F2 · 100%
vulnerable-nodejs90 F2 · 100%
vc-kimi-code-seeded-v2-legal-case-django90 F2 · 100%
vc-codex-high-seeded-v3-logistics-dispatch-fastify-vue90 F2 · 98%
vc-codex-high-seeded-v2-hr-payroll-django89 F2 · 96%
vc-codex-high-seeded-v3-healthcare-clinic-nextjs89 F2 · 95%
vc-claude-code-seeded-v3-support-desk-nestjs-angular88 F2 · 100%
vc-claude-code-seeded-v3-legal-case-remix88 F2 · 96%
dsvpwa87 F2 · 94%
vulnerable-node87 F2 · 95%
juice-shop-goof87 F2 · 96%
dvna87 F2 · 100%
vc-kimi-code-seeded-v3-fintech-lending-express87 F2 · 93%
vc-codex-high-seeded-v3-support-desk-nestjs-angular86 F2 · 94%
dvblab86 F2 · 91%
vulnnodeapp86 F2 · 90%
vc-codex-high-seeded-v3-education-lms-nextjs86 F2 · 90%
vc-kimi-code-seeded-v2-hr-payroll-django85 F2 · 97%
vc-deepseek-v4-flash-seeded-v3-logistics-dispatch-fastify-vue85 F2 · 100%
vc-kimi-code-seeded-v3-legal-case-remix84 F2 · 90%
vc-codex-high-seeded-v3-marketplace-commerce-express84 F2 · 89%
nextjs-vulnerable-app83 F2 · 100%
vc-codex-high-seeded-v3-crm-saas-nestjs-angular83 F2 · 89%
vc-deepseek-v4-flash-seeded-v3-marketplace-commerce-express83 F2 · 90%
vulnerable-app-angular82 F2 · 100%
vc-deepseek-v4-pro-seeded-v3-hr-payroll-remix82 F2 · 88%
vc-deepseek-v4-flash-seeded-v3-crm-saas-nestjs-angular81 F2 · 95%
vc-deepseek-v4-flash-seeded-v3-healthcare-clinic-nextjs80 F2 · 88%
vc-kimi-code-seeded-v3-property-management-fastify-vue80 F2 · 94%
vc-codex-high-seeded-v3-fintech-lending-express80 F2 · 82%
vc-kimi-code-seeded-v3-logistics-dispatch-fastify-vue78 F2 · 86%
vc-claude-code-seeded-v3-education-lms-nextjs78 F2 · 87%
vc-deepseek-v4-flash-seeded-v3-support-desk-nestjs-angular78 F2 · 88%
damn-vulnerable-graphql-application77 F2 · 78%
vc-codex-seeded-v2-fintech-lending-fastapi77 F2 · 76%
vc-deepseek-v4-pro-seeded-v3-legal-case-remix77 F2 · 88%
vc-codex-high-seeded-v3-legal-case-remix76 F2 · 79%
vc-kimi-code-seeded-v3-marketplace-commerce-express76 F2 · 91%
vc-claude-code-seeded-v3-fintech-lending-express76 F2 · 80%
ninjasworkout75 F2 · 91%
vc-deepseek-v4-flash-seeded-v3-legal-case-remix75 F2 · 91%
nodegoat74 F2 · 79%
threatbyte74 F2 · 77%
vc-kimi-code-seeded-v2-property-management-fastapi74 F2 · 80%
vc-kimi-code-seeded-v2-fintech-lending-fastapi74 F2 · 76%
vc-codex-high-seeded-v2-support-desk-fastapi74 F2 · 79%
vc-codex-high-seeded-v2-education-lms-django74 F2 · 76%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi73 F2 · 76%
vc-kimi-code-seeded-v2-support-desk-fastapi73 F2 · 79%
extremely-vulnerable-flask-app72 F2 · 72%
dvpwa71 F2 · 70%
python-app71 F2 · 67%
xvna69 F2 · 83%
vc-deepseek-v4-pro-seeded-v3-support-desk-nestjs-angular69 F2 · 100%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi68 F2 · 77%
vulnerable-tornado-app68 F2 · 71%
vc-claude-code-seeded-v3-healthcare-clinic-nextjs67 F2 · 67%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi67 F2 · 66%
vc-codex-high-seeded-v2-crm-saas-django66 F2 · 68%
vc-deepseek-v4-flash-seeded-v3-property-management-fastify-vue66 F2 · 92%
vuln-node-express65 F2 · 60%
vulnerable-api65 F2 · 64%
vc-deepseek-v4-pro-seeded-v3-fintech-lending-express64 F2 · 74%
owasp-web-playground64 F2 · 64%
python-insecure-app64 F2 · 62%
vc-claude-code-seeded-v3-logistics-dispatch-fastify-vue63 F2 · 65%
vc-codex-seeded-v2-property-management-fastapi62 F2 · 61%
vulnerable-rest-api-owasp-202361 F2 · 80%
vc-claude-code-seeded-v3-property-management-fastify-vue58 F2 · 69%
vulnpy54 F2 · 50%
flask-xss54 F2 · 50%
vulnerable-flask-app53 F2 · 52%
vulpy53 F2 · 51%
vc-codex-seeded-v2-marketplace-commerce-fastapi52 F2 · 48%
pygoat52 F2 · 50%
vc-codex-high-seeded-v3-hr-payroll-remix51 F2 · 52%
vc-deepseek-v4-pro-seeded-v3-marketplace-commerce-express50 F2 · 54%
nodejs-goof50 F2 · 53%
vc-deepseek-v4-flash-seeded-v3-hr-payroll-remix49 F2 · 61%
damn-vulnerable-flask-application49 F2 · 50%
vc-kimi-code-seeded-v3-education-lms-nextjs47 F2 · 52%
oss-oopssec-store47 F2 · 50%
react-security46 F2 · 57%
djangoat46 F2 · 44%
vc-kimi-code-seeded-v3-support-desk-nestjs-angular46 F2 · 50%
vc-kimi-code-seeded-v3-healthcare-clinic-nextjs46 F2 · 50%
vuln-node-express-swagger46 F2 · 47%
vc-deepseek-v4-pro-seeded-v3-healthcare-clinic-nextjs45 F2 · 50%
vc-deepseek-v4-flash-seeded-v3-fintech-lending-express44 F2 · 55%
vc-deepseek-v4-pro-seeded-v3-logistics-dispatch-fastify-vue43 F2 · 53%
vulnerable-react-fatih41 F2 · 57%
reactvulna38 F2 · 100%
vc-deepseek-v4-pro-seeded-v3-education-lms-nextjs37 F2 · 41%
vc-deepseek-v4-pro-seeded-v3-crm-saas-nestjs-angular36 F2 · 37%
vc-codex-high-seeded-v2-legal-case-django30 F2 · 32%
vulnerable-python-apps29 F2 · 27%
RepositoryTPFPFNRecall %F2
intentionally-vulnerable-python-application700100.0100.0
juice-shop8100100.0100.0
lets-be-bad-guys2400100.0100.0
pythonssti200100.0100.0
react-test-bench100100.0100.0
simply-vulnerable-react100100.0100.0
vampi1500100.0100.0
vfapi900100.0100.0
vc-claude-code-seeded-v2-education-lms-django3200100.0100.0
vc-claude-code-seeded-v2-legal-case-django3100100.0100.0
vc-claude-code-seeded-v3-crm-saas-nestjs-angular4900100.0100.0
vc-codex-high-seeded-v2-fintech-lending-fastapi2900100.0100.0
vc-codex-high-seeded-v3-property-management-fastify-vue4200100.0100.0
vc-codex-seeded-v2-education-lms-django3500100.0100.0
vc-codex-seeded-v2-healthcare-clinic-django4100100.0100.0
vc-codex-seeded-v2-support-desk-fastapi3000100.0100.0
vc-deepseek-v4-pro-seeded-v3-property-management-fastify-vue1900100.0100.0
vc-kimi-code-seeded-v2-healthcare-clinic-django3000100.0100.0
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi2700100.0100.0
vc-kimi-code-seeded-v3-crm-saas-nestjs-angular4000100.0100.0
vc-kimi-code-seeded-v3-hr-payroll-remix3600100.0100.0
vc-claude-code-seeded-v3-hr-payroll-remix3710100.099.5
vc-claude-code-seeded-v2-support-desk-fastapi3420100.098.8
vc-codex-seeded-v2-crm-saas-django3420100.098.8
vc-claude-code-seeded-v2-hr-payroll-django2720100.098.5
vc-claude-code-seeded-v2-property-management-fastapi3330100.098.2
insecure-web910100.097.8
vc-codex-seeded-v2-legal-case-django3340100.097.6
vc-claude-code-seeded-v2-crm-saas-django2840100.097.2
vc-codex-high-seeded-v2-healthcare-clinic-django2640100.097.0
vc-claude-code-seeded-v3-marketplace-commerce-express4080100.096.2
dvws-node77160100.096.0
dsvw262196.395.6
vc-codex-seeded-v2-hr-payroll-django372294.994.9
vc-claude-code-seeded-v2-logistics-dispatch-fastapi3390100.094.8
vc-codex-high-seeded-v2-property-management-fastapi2680100.094.2
vc-codex-high-seeded-v2-marketplace-commerce-fastapi2580100.094.0
vc-kimi-code-seeded-v2-crm-saas-django2790100.093.8
vc-claude-code-seeded-v2-healthcare-clinic-django29100100.093.5
vc-deepseek-v4-flash-seeded-v3-education-lms-nextjs28100100.093.3
vc-claude-code-seeded-v2-fintech-lending-fastapi29120100.092.4
node-api-goat730100.092.1
vc-codex-seeded-v2-logistics-dispatch-fastapi30130100.092.0
vc-kimi-code-seeded-v2-education-lms-django28130100.091.5
ivna1990100.091.3
vulnerable-nodejs19100100.090.5
vc-kimi-code-seeded-v2-legal-case-django26140100.090.3
vc-codex-high-seeded-v3-logistics-dispatch-fastify-vue4420197.890.2
vc-codex-high-seeded-v2-hr-payroll-django2411196.088.9
vc-codex-high-seeded-v3-healthcare-clinic-nextjs4017295.288.9
vc-claude-code-seeded-v3-support-desk-nestjs-angular41280100.088.0
vc-claude-code-seeded-v3-legal-case-remix2715196.487.7
dsvpwa3014293.887.2
vulnerable-node2011195.287.0
juice-shop-goof4929296.186.9
dvna17130100.086.7
vc-kimi-code-seeded-v3-fintech-lending-express3918392.986.7
vc-codex-high-seeded-v3-support-desk-nestjs-angular3318294.386.4
dvblab208290.986.2
vulnnodeapp269389.786.1
vc-codex-high-seeded-v3-education-lms-nextjs4315589.686.0
vc-kimi-code-seeded-v2-hr-payroll-django2820196.585.4
vc-deepseek-v4-flash-seeded-v3-logistics-dispatch-fastify-vue28250100.084.8
vc-kimi-code-seeded-v3-legal-case-remix3718490.284.5
vc-codex-high-seeded-v3-marketplace-commerce-express3917588.684.1
nextjs-vulnerable-app110100.083.3
vc-codex-high-seeded-v3-crm-saas-nestjs-angular3317489.283.3
vc-deepseek-v4-flash-seeded-v3-marketplace-commerce-express1911290.583.3
vulnerable-app-angular890100.081.6
vc-deepseek-v4-pro-seeded-v3-hr-payroll-remix2314388.581.6
vc-deepseek-v4-flash-seeded-v3-crm-saas-nestjs-angular2121195.580.8
vc-deepseek-v4-flash-seeded-v3-healthcare-clinic-nextjs2114387.580.2
vc-kimi-code-seeded-v3-property-management-fastify-vue3030293.879.8
vc-codex-high-seeded-v3-fintech-lending-express3213782.079.6
vc-kimi-code-seeded-v3-logistics-dispatch-fastify-vue3828686.478.5
vc-claude-code-seeded-v3-education-lms-nextjs3327586.877.8
vc-deepseek-v4-flash-seeded-v3-support-desk-nestjs-angular2118387.577.8
damn-vulnerable-graphql-application2810877.876.9
vc-codex-seeded-v2-fintech-lending-fastapi286975.776.9
vc-deepseek-v4-pro-seeded-v3-legal-case-remix2221388.076.9
vc-codex-high-seeded-v3-legal-case-remix37171078.776.4
vc-kimi-code-seeded-v3-marketplace-commerce-express3945490.776.2
vc-claude-code-seeded-v3-fintech-lending-express3220880.075.5
ninjasworkout2025290.975.2
vc-deepseek-v4-flash-seeded-v3-legal-case-remix2026290.974.6
nodegoat2214678.674.3
threatbyte2011676.974.1
vc-kimi-code-seeded-v2-property-management-fastapi2418680.074.1
vc-kimi-code-seeded-v2-fintech-lending-fastapi2512875.874.0
vc-codex-high-seeded-v2-support-desk-fastapi2215678.673.8
vc-codex-high-seeded-v2-education-lms-django1910676.073.6
vc-codex-high-seeded-v2-logistics-dispatch-fastapi2212775.973.3
vc-kimi-code-seeded-v2-support-desk-fastapi2216678.673.3
extremely-vulnerable-flask-app238971.972.3
dvpwa165769.670.8
python-app141766.770.7
xvna1014283.369.4
vc-deepseek-v4-pro-seeded-v3-support-desk-nestjs-angular19420100.069.3
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi2428777.468.2
vulnerable-tornado-app108471.467.6
vc-claude-code-seeded-v3-healthcare-clinic-nextjs29141467.467.4
vc-claude-code-seeded-v2-marketplace-commerce-fastapi2171165.667.3
vc-codex-high-seeded-v2-crm-saas-django1711868.066.4
vc-deepseek-v4-flash-seeded-v3-property-management-fastify-vue2352292.065.7
vuln-node-express30260.065.2
vulnerable-api94564.365.2
vc-deepseek-v4-pro-seeded-v3-fintech-lending-express2027774.164.5
owasp-web-playground18101064.364.3
python-insecure-app52362.564.1
vc-claude-code-seeded-v3-logistics-dispatch-fastify-vue33261864.762.7
vc-codex-seeded-v2-property-management-fastapi19111261.361.7
vulnerable-rest-api-owasp-20231227380.060.6
vc-claude-code-seeded-v3-property-management-fastify-vue22381068.858.5
vulnpy4094050.054.2
flask-xss1551550.053.6
vulnerable-flask-app1181052.453.4
vulpy29172850.952.9
vc-codex-seeded-v2-marketplace-commerce-fastapi1441548.352.2
pygoat39283950.051.5
vc-codex-high-seeded-v3-hr-payroll-remix22252052.451.2
vc-deepseek-v4-pro-seeded-v3-marketplace-commerce-express14211253.850.4
nodejs-goof913852.950.0
vc-deepseek-v4-flash-seeded-v3-hr-payroll-remix1130761.148.7
damn-vulnerable-flask-application79750.048.6
vc-kimi-code-seeded-v3-education-lms-nextjs24482252.246.9
oss-oopssec-store20342050.046.7
react-security411357.146.5
djangoat23182944.246.2
vc-kimi-code-seeded-v3-support-desk-nestjs-angular16301650.046.0
vc-kimi-code-seeded-v3-healthcare-clinic-nextjs18351850.045.7
vuln-node-express-swagger23342646.945.5
vc-deepseek-v4-pro-seeded-v3-healthcare-clinic-nextjs13281350.044.8
vc-deepseek-v4-flash-seeded-v3-fintech-lending-express12351054.544.4
vc-deepseek-v4-pro-seeded-v3-logistics-dispatch-fastify-vue16511453.342.8
vulnerable-react-fatih417357.140.8
reactvulna180100.038.5
vc-deepseek-v4-pro-seeded-v3-education-lms-nextjs11311640.736.7
vc-deepseek-v4-pro-seeded-v3-crm-saas-nestjs-angular11221936.735.9
vc-codex-high-seeded-v2-legal-case-django8251732.030.1
vulnerable-python-apps681627.329.4
§

Detection by severity

SeverityTPFPFNRecall %
Critical14401491.1
High2350049882.5
Medium776219080.3
Low11305368.1
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
Open Redirect870198.9
Command / OS Injection1310596.3
XPath Injection160194.1
Insecure Deserialization450393.8
Path Traversal950991.3
XML External Entities580690.6
SQL Injection13901590.3
Code Injection / RFI720890.0
Broken Access Control / IDOR20402887.9
Security Misconfiguration17403085.3
Server-Side Request Forgery7711682.8
Cross-Site Scripting16803881.6
Sensitive Data Exposure28206780.8
Other1507037879.9
Missing Authentication / Authorization12504872.3
Denial of Service6102670.1
Hardcoded Credentials14117565.3
HTTP Header Injection10150.0
§

LLM operational metrics

2,616,467
Avg input tokens
24,111
Avg output tokens
2,653,601
Avg total tokens
347s
Avg latency / repo
0.0%
JSON repair rate
140
Total runs
§

Cost

$548
Total cost
$3.91
Cost / run
$0.074
Cost / 100 LOC
741,034
Lines of code scanned
140
Successful runs

← Back to the leaderboard