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

GLM-5.3 by Z.ai ↗

General-Purpose LLM · agentic-v1 · scored on 136/140 repositories. Strict scoring (unfinished repos counted as misses).

Methodology note
136/140; strict scoring. GLM-5.3 through the standard agentic-v1 harness on Z.ai's API. All 66 Python repositories at F3 63.3; 70 of 74 TypeScript / JS. The four unfinished TS/JS repositories count as misses, giving F3 47.4 on TS/JS and 54.6 Overall (51.3 and 56.9 scored on completed repositories only) — fourth Overall, the best open-weight result in the benchmark. The retained raw output shows the four failures were the harness, not the model: in three the headless agent auto-rejected a permission prompt (reading a .env file, or a scratch write to /tmp) and ended the session before any findings were written; in one the model hit its output-length limit mid-answer. That permission behaviour is fixed as of 3.1.0 (see the DeepSeek V4.1 Flash note); the four repositories will be re-run under the fixed harness in a future release. Total spend $105.73, including one retry pass.
54.6
F3 (strict)
53.3
F2 (strict)
55.9%
Recall (strict)
44.9%
Precision
136/140
Repos scored
glm-5.3
Model
$106
Total cost
519s
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)
vuln-node-express96 F2 · 100%
vfapi96 F2 · 100%
pythonssti91 F2 · 100%
dsvw85 F2 · 85%
react-test-bench83 F2 · 100%
dvblab78 F2 · 82%
dsvpwa78 F2 · 81%
vc-codex-high-seeded-v2-crm-saas-django77 F2 · 76%
owasp-web-playground76 F2 · 89%
node-api-goat75 F2 · 86%
python-app75 F2 · 76%
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi75 F2 · 81%
vampi73 F2 · 80%
vc-codex-high-seeded-v2-hr-payroll-django73 F2 · 72%
vulnerable-tornado-app71 F2 · 71%
vc-codex-high-seeded-v2-marketplace-commerce-fastapi71 F2 · 72%
vc-codex-high-seeded-v2-property-management-fastapi70 F2 · 77%
insecure-web70 F2 · 78%
lets-be-bad-guys70 F2 · 71%
intentionally-vulnerable-python-application69 F2 · 71%
vulnerable-api69 F2 · 71%
vc-codex-seeded-v2-logistics-dispatch-fastapi69 F2 · 70%
vc-kimi-code-seeded-v2-property-management-fastapi69 F2 · 77%
dvna68 F2 · 71%
vc-claude-code-seeded-v2-property-management-fastapi68 F2 · 64%
vulnerable-flask-app68 F2 · 71%
vc-codex-high-seeded-v2-support-desk-fastapi67 F2 · 64%
vulnerable-node67 F2 · 71%
vc-codex-high-seeded-v2-healthcare-clinic-django67 F2 · 69%
vc-kimi-code-seeded-v2-education-lms-django67 F2 · 71%
vc-kimi-code-seeded-v2-support-desk-fastapi66 F2 · 68%
threatbyte66 F2 · 65%
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi66 F2 · 81%
vc-codex-high-seeded-v2-education-lms-django66 F2 · 72%
vulnpy66 F2 · 65%
vc-kimi-code-seeded-v2-healthcare-clinic-django65 F2 · 70%
vc-kimi-code-seeded-v2-legal-case-django65 F2 · 69%
vc-claude-code-seeded-v3-fintech-lending-express64 F2 · 70%
vc-codex-seeded-v2-legal-case-django64 F2 · 64%
vc-codex-high-seeded-v2-logistics-dispatch-fastapi63 F2 · 66%
damn-vulnerable-graphql-application63 F2 · 69%
vc-kimi-code-seeded-v2-hr-payroll-django62 F2 · 66%
vc-kimi-code-seeded-v2-fintech-lending-fastapi62 F2 · 64%
vc-claude-code-seeded-v2-fintech-lending-fastapi62 F2 · 62%
vc-claude-code-seeded-v2-education-lms-django61 F2 · 59%
vc-claude-code-seeded-v2-marketplace-commerce-fastapi61 F2 · 59%
vc-kimi-code-seeded-v2-crm-saas-django61 F2 · 63%
vc-deepseek-v4-flash-seeded-v3-legal-case-remix61 F2 · 68%
extremely-vulnerable-flask-app61 F2 · 59%
vc-claude-code-seeded-v2-support-desk-fastapi61 F2 · 59%
vc-claude-code-seeded-v2-logistics-dispatch-fastapi60 F2 · 58%
vc-codex-seeded-v2-hr-payroll-django60 F2 · 59%
vc-claude-code-seeded-v2-crm-saas-django60 F2 · 61%
vc-codex-seeded-v2-crm-saas-django60 F2 · 62%
vc-codex-seeded-v2-education-lms-django60 F2 · 60%
vulnerable-python-apps60 F2 · 59%
vc-codex-high-seeded-v2-fintech-lending-fastapi59 F2 · 66%
vc-codex-seeded-v2-property-management-fastapi59 F2 · 58%
vc-kimi-code-seeded-v3-fintech-lending-express59 F2 · 64%
vc-codex-seeded-v2-support-desk-fastapi59 F2 · 57%
dvpwa59 F2 · 57%
pygoat59 F2 · 58%
vc-claude-code-seeded-v2-legal-case-django58 F2 · 55%
vc-claude-code-seeded-v3-property-management-fastify-vue58 F2 · 69%
vc-codex-high-seeded-v3-support-desk-nestjs-angular58 F2 · 66%
vc-codex-high-seeded-v3-legal-case-remix57 F2 · 57%
vc-codex-seeded-v2-healthcare-clinic-django57 F2 · 56%
vc-claude-code-seeded-v3-support-desk-nestjs-angular57 F2 · 63%
vc-kimi-code-seeded-v3-legal-case-remix56 F2 · 66%
vc-codex-high-seeded-v3-education-lms-nextjs56 F2 · 65%
nodejs-goof56 F2 · 65%
vc-claude-code-seeded-v2-healthcare-clinic-django56 F2 · 55%
djangoat55 F2 · 54%
vc-claude-code-seeded-v3-logistics-dispatch-fastify-vue55 F2 · 57%
vc-claude-code-seeded-v2-hr-payroll-django55 F2 · 52%
vc-codex-high-seeded-v3-healthcare-clinic-nextjs55 F2 · 60%
ivna54 F2 · 58%
vc-claude-code-seeded-v3-legal-case-remix54 F2 · 61%
vc-claude-code-seeded-v3-education-lms-nextjs54 F2 · 63%
vc-deepseek-v4-flash-seeded-v3-education-lms-nextjs54 F2 · 57%
vc-kimi-code-seeded-v3-logistics-dispatch-fastify-vue54 F2 · 59%
vc-codex-seeded-v2-marketplace-commerce-fastapi54 F2 · 55%
vc-claude-code-seeded-v3-hr-payroll-remix53 F2 · 57%
vc-codex-high-seeded-v3-hr-payroll-remix53 F2 · 57%
vc-deepseek-v4-flash-seeded-v3-healthcare-clinic-nextjs53 F2 · 58%
vc-kimi-code-seeded-v3-hr-payroll-remix53 F2 · 56%
vulpy52 F2 · 51%
vc-claude-code-seeded-v3-marketplace-commerce-express52 F2 · 52%
flask-xss51 F2 · 47%
vulnerable-app-angular51 F2 · 62%
vc-kimi-code-seeded-v3-property-management-fastify-vue51 F2 · 59%
vc-codex-high-seeded-v3-property-management-fastify-vue51 F2 · 52%
vc-codex-high-seeded-v3-crm-saas-nestjs-angular50 F2 · 51%
nextjs-vulnerable-app50 F2 · 100%
vc-deepseek-v4-flash-seeded-v3-property-management-fastify-vue50 F2 · 60%
vc-claude-code-seeded-v3-crm-saas-nestjs-angular50 F2 · 49%
vc-kimi-code-seeded-v3-marketplace-commerce-express49 F2 · 53%
python-insecure-app49 F2 · 50%
vulnerable-rest-api-owasp-202349 F2 · 80%
vc-codex-high-seeded-v3-fintech-lending-express48 F2 · 51%
ninjasworkout48 F2 · 59%
vc-codex-high-seeded-v3-logistics-dispatch-fastify-vue48 F2 · 49%
vc-deepseek-v4-flash-seeded-v3-support-desk-nestjs-angular48 F2 · 54%
vc-deepseek-v4-pro-seeded-v3-property-management-fastify-vue47 F2 · 68%
vc-kimi-code-seeded-v3-healthcare-clinic-nextjs47 F2 · 53%
vc-deepseek-v4-pro-seeded-v3-logistics-dispatch-fastify-vue47 F2 · 50%
vc-deepseek-v4-pro-seeded-v3-marketplace-commerce-express46 F2 · 46%
vuln-node-express-swagger46 F2 · 49%
nodegoat46 F2 · 46%
vulnnodeapp46 F2 · 48%
oss-oopssec-store45 F2 · 48%
vc-codex-seeded-v2-fintech-lending-fastapi45 F2 · 43%
vulnerable-nodejs45 F2 · 47%
vc-kimi-code-seeded-v3-support-desk-nestjs-angular44 F2 · 53%
vc-deepseek-v4-pro-seeded-v3-education-lms-nextjs44 F2 · 48%
vc-deepseek-v4-flash-seeded-v3-crm-saas-nestjs-angular44 F2 · 64%
vc-deepseek-v4-flash-seeded-v3-hr-payroll-remix43 F2 · 50%
vc-kimi-code-seeded-v3-crm-saas-nestjs-angular42 F2 · 48%
xvna42 F2 · 58%
vc-deepseek-v4-flash-seeded-v3-fintech-lending-express41 F2 · 50%
vc-deepseek-v4-pro-seeded-v3-healthcare-clinic-nextjs41 F2 · 50%
vc-deepseek-v4-pro-seeded-v3-legal-case-remix41 F2 · 48%
vc-claude-code-seeded-v3-healthcare-clinic-nextjs41 F2 · 44%
vc-deepseek-v4-flash-seeded-v3-marketplace-commerce-express40 F2 · 48%
react-security40 F2 · 57%
vc-deepseek-v4-flash-seeded-v3-logistics-dispatch-fastify-vue39 F2 · 39%
vc-deepseek-v4-pro-seeded-v3-support-desk-nestjs-angular38 F2 · 47%
juice-shop-goof34 F2 · 35%
vc-deepseek-v4-pro-seeded-v3-hr-payroll-remix34 F2 · 38%
juice-shop30 F2 · 28%
vc-deepseek-v4-pro-seeded-v3-crm-saas-nestjs-angular29 F2 · 33%
damn-vulnerable-flask-application29 F2 · 29%
vc-codex-high-seeded-v2-legal-case-django24 F2 · 24%
simply-vulnerable-react23 F2 · 100%
vulnerable-react-fatih16 F2 · 29%
reactvulna0 F2 · 0%
RepositoryTPFPFNRecall %F2
vuln-node-express510100.096.2
vfapi920100.095.7
pythonssti210100.090.9
dsvw235485.284.6
react-test-bench110100.083.3
dvblab189481.878.3
dsvpwa2613681.277.8
vc-codex-high-seeded-v2-crm-saas-django194676.077.2
owasp-web-playground2527389.376.2
node-api-goat66185.775.0
python-app167576.274.8
vc-kimi-code-seeded-v2-marketplace-commerce-fastapi2217581.574.8
vampi1210380.073.2
vc-codex-high-seeded-v2-hr-payroll-django186772.072.6
vulnerable-tornado-app104471.471.4
vc-codex-high-seeded-v2-marketplace-commerce-fastapi188772.071.4
vc-codex-high-seeded-v2-property-management-fastapi2018676.970.4
insecure-web77277.870.0
lets-be-bad-guys179770.869.7
intentionally-vulnerable-python-application53271.469.4
vulnerable-api106471.469.4
vc-codex-seeded-v2-logistics-dispatch-fastapi2111970.069.1
vc-kimi-code-seeded-v2-property-management-fastapi2324776.768.9
dvna128570.668.2
vc-claude-code-seeded-v2-property-management-fastapi2121263.667.7
vulnerable-flask-app1512671.467.6
vc-codex-high-seeded-v2-support-desk-fastapi1841064.367.2
vulnerable-node1513671.467.0
vc-codex-high-seeded-v2-healthcare-clinic-django1813869.266.7
vc-kimi-code-seeded-v2-education-lms-django2018871.466.7
vc-kimi-code-seeded-v2-support-desk-fastapi1912967.966.4
threatbyte178965.465.9
vc-kimi-code-seeded-v2-logistics-dispatch-fastapi2541680.765.8
vc-codex-high-seeded-v2-education-lms-django1819772.065.7
vulnpy52252865.065.5
vc-kimi-code-seeded-v2-healthcare-clinic-django2121970.064.8
vc-kimi-code-seeded-v2-legal-case-django1817869.264.7
vc-claude-code-seeded-v3-fintech-lending-express28291270.064.5
vc-codex-seeded-v2-legal-case-django21111263.664.0
vc-codex-high-seeded-v2-logistics-dispatch-fastapi19151065.563.3
damn-vulnerable-graphql-application25301169.462.8
vc-kimi-code-seeded-v2-hr-payroll-django19171065.562.5
vc-kimi-code-seeded-v2-fintech-lending-fastapi21161263.662.1
vc-claude-code-seeded-v2-fintech-lending-fastapi18121162.161.6
vc-claude-code-seeded-v2-education-lms-django1981359.461.3
vc-claude-code-seeded-v2-marketplace-commerce-fastapi1981359.461.3
vc-kimi-code-seeded-v2-crm-saas-django17141063.061.2
vc-deepseek-v4-flash-seeded-v3-legal-case-remix1520768.261.0
extremely-vulnerable-flask-app1991359.460.9
vc-claude-code-seeded-v2-support-desk-fastapi2091458.860.6
vc-claude-code-seeded-v2-logistics-dispatch-fastapi1961457.660.5
vc-codex-seeded-v2-hr-payroll-django23111659.060.5
vc-claude-code-seeded-v2-crm-saas-django17121160.760.3
vc-codex-seeded-v2-crm-saas-django21171361.860.3
vc-codex-seeded-v2-education-lms-django21141460.060.0
vulnerable-python-apps138959.159.6
vc-codex-high-seeded-v2-fintech-lending-fastapi19251065.559.4
vc-codex-seeded-v2-property-management-fastapi18101358.159.2
vc-kimi-code-seeded-v3-fintech-lending-express27331564.359.2
vc-codex-seeded-v2-support-desk-fastapi1771356.759.0
dvpwa1361056.558.6
pygoat45273357.758.6
vc-claude-code-seeded-v2-legal-case-django1751454.858.2
vc-claude-code-seeded-v3-property-management-fastify-vue22391068.858.2
vc-codex-high-seeded-v3-support-desk-nestjs-angular23361265.757.8
vc-codex-high-seeded-v3-legal-case-remix27202057.557.4
vc-codex-seeded-v2-healthcare-clinic-django23151856.156.9
vc-claude-code-seeded-v3-support-desk-nestjs-angular26391563.456.8
vc-kimi-code-seeded-v3-legal-case-remix27481465.856.5
vc-codex-high-seeded-v3-education-lms-nextjs31521764.656.4
nodejs-goof1119664.756.1
vc-claude-code-seeded-v2-healthcare-clinic-django16121355.255.6
djangoat28172453.855.3
vc-claude-code-seeded-v3-logistics-dispatch-fastify-vue29292256.955.3
vc-claude-code-seeded-v2-hr-payroll-django1451351.855.1
vc-codex-high-seeded-v3-healthcare-clinic-nextjs25351759.554.8
ivna1114857.954.5
vc-claude-code-seeded-v3-legal-case-remix17271160.754.5
vc-claude-code-seeded-v3-education-lms-nextjs24451463.254.3
vc-deepseek-v4-flash-seeded-v3-education-lms-nextjs16201257.154.1
vc-kimi-code-seeded-v3-logistics-dispatch-fastify-vue26391859.153.9
vc-codex-seeded-v2-marketplace-commerce-fastapi16171355.253.7
vc-claude-code-seeded-v3-hr-payroll-remix21281656.853.3
vc-codex-high-seeded-v3-hr-payroll-remix24331857.153.3
vc-deepseek-v4-flash-seeded-v3-healthcare-clinic-nextjs14221058.353.0
vc-kimi-code-seeded-v3-hr-payroll-remix20251655.652.9
vulpy29222850.952.0
vc-claude-code-seeded-v3-marketplace-commerce-express21211952.552.0
flask-xss1431646.751.1
vulnerable-app-angular512362.551.0
vc-kimi-code-seeded-v3-property-management-fastify-vue19401359.450.8
vc-codex-high-seeded-v3-property-management-fastify-vue22272052.450.7
vc-codex-high-seeded-v3-crm-saas-nestjs-angular19211851.350.5
nextjs-vulnerable-app150100.050.0
vc-deepseek-v4-flash-seeded-v3-property-management-fastify-vue15351060.050.0
vc-claude-code-seeded-v3-crm-saas-nestjs-angular24222549.049.6
vc-kimi-code-seeded-v3-marketplace-commerce-express23392053.549.1
python-insecure-app45450.048.8
vulnerable-rest-api-owasp-20231251380.048.8
vc-codex-high-seeded-v3-fintech-lending-express20301951.348.5
ninjasworkout1335959.147.8
vc-codex-high-seeded-v3-logistics-dispatch-fastify-vue22282348.947.8
vc-deepseek-v4-flash-seeded-v3-support-desk-nestjs-angular13271154.247.8
vc-deepseek-v4-pro-seeded-v3-property-management-fastify-vue1348668.447.4
vc-kimi-code-seeded-v3-healthcare-clinic-nextjs19381752.847.3
vc-deepseek-v4-pro-seeded-v3-logistics-dispatch-fastify-vue15251550.046.9
vc-deepseek-v4-pro-seeded-v3-marketplace-commerce-express12131446.246.5
vuln-node-express-swagger24392549.046.3
nodegoat13161546.446.1
vulnnodeapp14221548.346.1
oss-oopssec-store19322147.545.0
vc-codex-seeded-v2-fintech-lending-fastapi16142143.244.9
vulnerable-nodejs9161047.444.6
vc-kimi-code-seeded-v3-support-desk-nestjs-angular17481553.144.0
vc-deepseek-v4-pro-seeded-v3-education-lms-nextjs13271448.143.9
vc-deepseek-v4-flash-seeded-v3-crm-saas-nestjs-angular1459863.643.5
vc-deepseek-v4-flash-seeded-v3-hr-payroll-remix923950.043.3
vc-kimi-code-seeded-v3-crm-saas-nestjs-angular19452147.542.4
xvna729558.341.7
vc-deepseek-v4-flash-seeded-v3-fintech-lending-express11341150.041.4
vc-deepseek-v4-pro-seeded-v3-healthcare-clinic-nextjs13401350.041.4
vc-deepseek-v4-pro-seeded-v3-legal-case-remix12331348.041.4
vc-claude-code-seeded-v3-healthcare-clinic-nextjs19402444.241.1
vc-deepseek-v4-flash-seeded-v3-marketplace-commerce-express10301147.640.3
react-security418357.140.0
vc-deepseek-v4-flash-seeded-v3-logistics-dispatch-fastify-vue11191739.338.7
vc-deepseek-v4-pro-seeded-v3-support-desk-nestjs-angular9331047.438.1
juice-shop-goof18453335.333.7
vc-deepseek-v4-pro-seeded-v3-hr-payroll-remix10351638.533.6
juice-shop23405828.429.7
vc-deepseek-v4-pro-seeded-v3-crm-saas-nestjs-angular10412033.329.2
damn-vulnerable-flask-application491028.629.0
vc-codex-high-seeded-v2-legal-case-django6211924.023.6
simply-vulnerable-react1170100.022.7
vulnerable-react-fatih232528.616.1
reactvulna01110.00.0
§

Detection by severity

SeverityTPFPFNRecall %
Critical14621093.6
High15810110158.9
Medium531643155.2
Low5708739.6
§

Detection by vulnerability class

CWE familyTPFPFNRecall %
Insecure Deserialization4700100.0
HTTP Header Injection200100.0
XPath Injection1300100.0
Command / OS Injection1240596.1
XML External Entities560493.3
Path Traversal910792.9
Code Injection / RFI720692.3
SQL Injection13401589.9
Open Redirect7301285.9
Server-Side Request Forgery7421583.1
Security Misconfiguration14405472.7
Cross-Site Scripting13506567.5
Denial of Service4603854.8
Hardcoded Credentials10919453.7
Missing Authentication / Authorization8637653.1
Sensitive Data Exposure156015949.5
Broken Access Control / IDOR104011747.1
Other849296246.9
§

LLM operational metrics

102,958
Avg input tokens
35,387
Avg output tokens
1,460,633
Avg total tokens
519s
Avg latency / repo
0.0%
JSON repair rate
140
Total runs
§

Cost

$106
Total cost
$0.78
Cost / run
$0.015
Cost / 100 LOC
713,729
Lines of code scanned
136
Successful runs

← Back to the leaderboard