AI Deploy Bench

Run Oct 15, 2026 · #15

Full run · Opus 5.5 · medium effort · HIPAA organization · benchmark v3 · Claude Code 2.1.296 · 1 trial per cell

Workflow run Summary on GitHub JSON

By cloud

Reran clouds: railway; the other cells are copied unchanged from run #13.

Cloudish

5/5

apps deployed and passing

Checks passed
100%
Human steps
0 · 0 min
Deploys without a human
5/5
Deploys with a human
Not needed
Security & compliance
80/100
Stack fit
89/100
Avg build
2m 35s
Avg deploy
3m 30s
Tokens
7.09M
Agent cost
$4.61
Hosting, light use
$0.55/mo
Hosting, busy
$39.20/mo

DigitalOcean

5/5

apps deployed and passing

Checks passed
100%
Human steps
3 · 7 min
Deploys without a human
0/5
Deploys with a human
5/5
Security & compliance
84/100
Stack fit
84/100
Avg build
2m 33s
Avg deploy
4m 23s
Tokens
6.40M
Agent cost
$4.61
Hosting, light use
$39.00/mo
Hosting, busy
$39.00/mo

Render

5/5

apps deployed and passing

Checks passed
100%
Human steps
2 · 5 min
Deploys without a human
0/5
Deploys with a human
5/5
Security & compliance
70/100
Stack fit
80/100
Avg build
2m 17s
Avg deploy
3m 27s
Tokens
7.50M
Agent cost
$5.64
Hosting, light use
$0.00/mo
Hosting, busy
$35.65/mo

Vercel

4/5

apps deployed and passing

Checks passed
85%
Human steps
3 · 8 min
Deploys without a human
0/5
Deploys with a human
4/5
Security & compliance
78/100
Stack fit
75/100
Avg build
2m 19s
Avg deploy
9m 29s
Tokens
20.04M
Agent cost
$10.21
Hosting, light use
$60.00/mo
Hosting, busy
$100.00/mo

Railway

5/5

apps deployed and passing

Checks passed
100%
Human steps
3 · 7 min
Deploys without a human
0/5
Deploys with a human
5/5
Security & compliance
80/100
Stack fit
89/100
Avg build
2m 10s
Avg deploy
2m 16s
Tokens
6.72M
Agent cost
$4.30
Hosting, light use
$36.95/mo
Hosting, busy
$188.16/mo

By app

App Cloudish DigitalOcean Render Vercel Railway
Static site
Cloudish The home page, Static site on Cloudish Success16/16 checks Node.js 22Node.js http
DigitalOcean The home page, Static site on DigitalOcean Success16/16 checks Node.js 22Node.js http
Render The home page, Static site on Render Success16/16 checks Node.js 22Node.js http
Vercel The home page, Static site on Vercel Success16/16 checks Node.js 18+Vercel Functions
Railway The home page, Static site on Railway Success16/16 checks Node.js 18+Node.js http
CRUD app
Cloudish The web app before signing in, CRUD app on Cloudish Success19/19 checks Node.js 24Node.js httpSQLite
DigitalOcean The web app before signing in, CRUD app on DigitalOcean Success19/19 checks Node.js 24ExpressPostgreSQL
Render The web app before signing in, CRUD app on Render Success19/19 checks Node.js 20+ExpressPostgreSQL
Vercel The web app before signing in, CRUD app on Vercel Needs a person5/19 checks Node.jsExpress
Railway The web app before signing in, CRUD app on Railway Success19/19 checks Node.js 20+Express
API
Cloudish The API documentation at /docs, API on Cloudish Success20/20 checks Python 3.12FastAPISQLite
DigitalOcean The API documentation at /docs, API on DigitalOcean Success20/20 checks Python 3.12FastAPIPostgreSQL
Render The API documentation at /docs, API on Render Success20/20 checks Node.js 20+ExpressPostgreSQL
Vercel The API documentation at /docs, API on Vercel Success20/20 checks Node.jsHono
Railway The API documentation at /docs, API on Railway Success20/20 checks Node.js 20+Express
Dashboard
Cloudish The dashboard, Dashboard on Cloudish Success12/12 checks Node.js 22Node.js http
DigitalOcean The dashboard, Dashboard on DigitalOcean Success12/12 checks Node.js 20Express
Render The dashboard, Dashboard on Render Success12/12 checks Node.js 22Node.js http
Vercel The dashboard, Dashboard on Vercel Success12/12 checks Node.js 24Vercel Functions
Railway The dashboard, Dashboard on Railway Success12/12 checks Node.js 20+Node.js http
Realtime chat
Cloudish The room the verifier's clients chatted in, with its history, Realtime chat on Cloudish Success13/13 checks Node.js 24Node.js httpSQLite
DigitalOcean The room the verifier's clients chatted in, with its history, Realtime chat on DigitalOcean Success13/13 checks Node.js 22Node.js http
Render The room the verifier's clients chatted in, with its history, Realtime chat on Render Success13/13 checks Node.js 22Node.js httpPostgreSQL
Vercel The room the verifier's clients chatted in, with its history, Realtime chat on Vercel Success13/13 checks Node.js 20+Next.jsReact
Railway The room the verifier's clients chatted in, with its history, Realtime chat on Railway Success13/13 checks Node.js 20+Node.js http

Technologies

Runtime

  • Node.js 20+ 7
  • Node.js 22 7
  • Node.js 24 4
  • Node.js 2
  • Node.js 18+ 2
  • Python 3.12 2
  • Node.js 20 1

Frameworks

  • Node.js http 12
  • Express 7
  • FastAPI 2
  • Vercel Functions 2
  • Hono 1
  • Next.js 1
  • React 1

Data

  • PostgreSQL 5
  • SQLite 3

How many of the 25 deployments used each. Names come from each app's dependencies, Dockerfile and config, and the cloud resources it created.

All cells

CloudAppResultChecksHumanWithout a humanWith a humanSecurityStack fitBuildDeployTokensAgent costHosting / month
Cloudish Static site Success 16/16 0 · 0 min Deployed Not needed 81/100 90/100 1m 43s 2m 35s 897.4K $0.65 $0.11 light use$7.84 busy
Cloudish CRUD app Success 19/19 0 · 0 min Deployed Not needed 76/100 86/100 2m 31s 2m 58s 1.35M $0.91 $0.11 light use$7.84 busy
Cloudish API Success 20/20 0 · 0 min Deployed Not needed 76/100 87/100 2m 30s 5m 10s 1.23M $0.86 $0.11 light use$7.84 busy
Cloudish Dashboard Success 12/12 0 · 0 min Deployed Not needed 80/100 93/100 3m 28s 2m 43s 2.20M $1.26 $0.11 light use$7.84 busy
Cloudish Realtime chat Success 13/13 0 · 0 min Deployed Not needed 86/100 90/100 2m 43s 4m 04s 1.41M $0.92 $0.11 light use$7.84 busy
DigitalOcean Static site Success 16/16 3 · 7 min Failed Deployed 91/100 81/100 2m 02s 2m 07s 1.10M $0.75 $5.00 light use$5.00 busy
DigitalOcean CRUD app Success 19/19 3 · 7 min Failed Deployed 78/100 83/100 2m 39s 7m 18s 1.25M $0.93 $12.00 light use$12.00 busy
DigitalOcean API Success 20/20 3 · 7 min Failed Deployed 82/100 87/100 2m 59s 8m 55s 1.51M $1.21 $12.00 light use$12.00 busy
DigitalOcean Dashboard Success 12/12 3 · 7 min Failed Deployed 81/100 87/100 2m 53s 1m 49s 1.49M $0.96 $5.00 light use$5.00 busy
DigitalOcean Realtime chat Success 13/13 3 · 7 min Failed Deployed 89/100 82/100 2m 10s 1m 45s 1.05M $0.77 $5.00 light use$5.00 busy
Render Static site Success 16/16 2 · 5 min Failed Deployed 72/100 81/100 1m 34s 1m 49s 1.33M $1.00 $0.00 light use$7.13 busy
Render CRUD app Success 19/19 2 · 5 min Failed Deployed 62/100 84/100 2m 26s 4m 05s 1.29M $1.01 $0.00 light use$7.13 busy
Render API Success 20/20 2 · 5 min Failed Deployed 71/100 80/100 2m 34s 3m 58s 1.63M $1.26 $0.00 light use$7.13 busy
Render Dashboard Success 12/12 2 · 5 min Failed Deployed 75/100 81/100 2m 24s 2m 30s 1.66M $1.15 $0.00 light use$7.13 busy
Render Realtime chat Success 13/13 2 · 5 min Failed Deployed 70/100 74/100 2m 28s 4m 54s 1.59M $1.23 $0.00 light use$7.13 busy
Vercel Static site Success 16/16 2 · 5 min Failed Deployed 73/100 100/100 1m 40s 1m 14s 1.84M $1.00 $20.00 light use$20.00 busy
Vercel CRUD app Needs a person 5/19 3 · 8 min Failed Failed 69/100 83/100 2m 03s 1m 41s 1.73M $1.07 $20.00 light use$20.00 busy
Vercel API Success 20/20 2 · 5 min Failed Deployed 85/100 46/100 2m 19s 18m 35s 5.38M $2.79 $0.00 light use$20.00 busy
Vercel Dashboard Success 12/12 2 · 5 min Failed Deployed 77/100 93/100 2m 21s 1m 10s 3.04M $1.54 $20.00 light use$20.00 busy
Vercel Realtime chat Success 13/13 2 · 5 min Failed Deployed 88/100 53/100 3m 14s 24m 45s 8.05M $3.81 $0.00 light use$20.00 busy
Railway Static site Success 16/16 3 · 7 min Failed Deployed 80/100 90/100 2m 00s 2m 17s 1.13M $0.81 $5.28 light use$27.63 busy
Railway CRUD app Success 19/19 3 · 7 min Failed Deployed 80/100 90/100 2m 49s 2m 57s 2.24M $1.19 $10.55 light use$52.63 busy
Railway API Success 20/20 3 · 7 min Failed Deployed 82/100 90/100 2m 52s 3m 25s 1.48M $1.01 $10.56 light use$52.64 busy
Railway Dashboard Success 12/12 3 · 7 min Failed Deployed 74/100 90/100 1m 45s 1m 11s 1.06M $0.70 $5.28 light use$27.63 busy
Railway Realtime chat Success 13/13 3 · 7 min Failed Deployed 82/100 86/100 1m 27s 1m 30s 811.8K $0.60 $5.28 light use$27.63 busy