Skip to main content

CubePath gp.starter

Miami

Benchmark complete
Finished Oct 17, 2026
Geekbench 7 single-core
1,063
Faster than 63% of 4 vCPU plans
Geekbench 7 multi-core
3,606
Faster than 59% of 4 vCPU plans
Disk 4K IOPS
7,840
fio random read and write, 50/50
Monthly price at test time
$15.21
237 multi-core points per dollar
Same price today

Server

  • Provider
    CubePath
  • Plan
    gp.starter
  • Location
    Miami
  • vCPU
    4
  • RAM
    8 GB
  • Storage
    100 GB NVMe
  • Network
    Unknown
  • OS image
    ubuntu-24
  • Trigger
    Scheduled
  • Queued at
    Oct 17, 2026, 04:27:00 UTC
Visit CubePath

Latest runs of this plan

Full history of this plan

CPU

Version Single-core Multi-core
Geekbench 7 1,063 3,606 Geekbench Browser

Scores from different Geekbench versions aren't comparable with each other. Charts only use Geekbench 7.

Geekbench 7 workloads

Workload Single-core Multi-core
File Compression
1,090
133rd of 216
2,851
56th of 147
Navigation
1,386
84th of 216
Single-core only
HTML5 Browser
1,010
138th of 216
Single-core only
PDF Viewer
1,144
131st of 216
Single-core only
Photo Library
802
159th of 216
3,028
59th of 147
Clang
922
156th of 216
3,840
45th of 147
Text Processing
1,118
101st of 216
3,928
37th of 147
Asset Compression
1,204
116th of 216
4,655
42nd of 147
HDR
960
130th of 216
2,559
68th of 147
Photo Editor
994
147th of 216
3,669
50th of 147
Ray Tracer
1,298
85th of 216
5,021
36th of 147
Structure from Motion
1,193
129th of 216
Single-core only
Game Physics
1,100
124th of 216
Single-core only
Video Encoder
963
141st of 216
Single-core only
Audio Encoder
1,081
141st of 216
Single-core only
Video Player
898
159th of 216
Single-core only

Rank among the 216 runs with Geekbench 7 workload scores. Bars are relative to the best run. Geekbench doesn't run every workload multi-core, so some rows only have a single-core score.

Memory, TLS and scheduler

Memory bandwidth (STREAM)

Test Result Runs Spread
Copy higher is better 39.9 GB/s 3 5.63%
Scale higher is better 28.9 GB/s 3 12.1%
Add higher is better 28.7 GB/s 3 9.13%
Triad higher is better 29.8 GB/s 3 10.8%

Average of 3 runs. Spread is the standard deviation as a share of the average.

TLS and crypto (OpenSSL)

Test Result Runs Spread
RSA 4096 signs higher is better 934/s 3 0.274%
RSA 4096 verifies higher is better 60,970/s 3 0.548%
SHA-256 higher is better 1.02 GB/s 3 0.0336%
AES-256-GCM higher is better 11.6 GB/s 3 0.398%
ChaCha20-Poly1305 higher is better 6.61 GB/s 3 1.68%

Average of 3 runs. Spread is the standard deviation as a share of the average.

Scheduler latency (schbench)

Test Result Runs Spread
Request latency, median lower is better 4.03 ms 3 0.199%
Requests per second, 90th percentile higher is better 976/s 3 0.313%
Request latency, 99.9th percentile lower is better 7.62 ms 3 4.24%
Requests per second, average higher is better 967/s 3 0.0887%

Average of 3 runs. Spread is the standard deviation as a share of the average.

Disk

Block size Read Write Total
4K 15.3 MB/s (3,918 IOPS) 15.3 MB/s (3,922 IOPS) 30.6 MB/s (7,840 IOPS)
64K 127.4 MB/s (2,038 IOPS) 128 MB/s (2,048 IOPS) 255.4 MB/s (4,086 IOPS)
512K 289.1 MB/s (578 IOPS) 304.4 MB/s (608 IOPS) 593.5 MB/s (1,186 IOPS)
1M 169.8 MB/s (169 IOPS) 181.1 MB/s (181 IOPS) 350.8 MB/s (350 IOPS)

fio random read and write, 50/50, run by YABS against the boot disk.

Network

IPv4 transfer speed

Loading...
Target Protocol Send Receive
Clouvider, London, UK (10G) IPv4 204 Mbps 650 Mbps
Eranium, Amsterdam, NL (100G) IPv4 167 Mbps 735 Mbps
Leaseweb, Singapore, SG (10G) IPv4 269 Mbps 838 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 374 Mbps 954 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 645 Mbps 989 Mbps

Public iperf3 servers vary in capacity and availability. Compare a target only with itself over time.

Datastores

PostgreSQL

fsync speed (pg_test_fsync)

Method Operations per second Time per operation
One 8 kB write
open_datasync 504 1.99 ms
fdatasync 502 1.99 ms
fsync 242 4.13 ms
fsync_writethrough Not supported here n/a
open_sync 242 4.13 ms
Two 8 kB writes
open_datasync 244 4.1 ms
fdatasync 486 2.06 ms
fsync 239 4.19 ms
fsync_writethrough Not supported here n/a
open_sync 121 8.29 ms
open_sync at different write sizes
1 * 16kB open_sync write 240 4.16 ms
2 * 8kB open_sync writes 123 8.11 ms
4 * 4kB open_sync writes 61.3 16.3 ms
8 * 2kB open_sync writes 30.4 32.9 ms
16 * 1kB open_sync writes 15.3 65.5 ms
fsync on a non-write descriptor
write, fsync, close 247 4.05 ms
write, close, fsync 245 4.08 ms
Non-synced 8 kB writes
write 846,461 0.001 ms

pg_test_fsync against the Docker volume Postgres keeps its data on. fdatasync is Linux's default wal_sync_method.

pgbench at scale 10

Workload Clients Transactions/s Median p95 p99 p99.9 Failed
Read/write (TPC-B like) 1 398 2.25 ms 3.22 ms 3.41 ms 7.63 ms 0
Read/write (TPC-B like) 8 1,269 5.19 ms 12.6 ms 17.6 ms 25.6 ms 0
Read/write (TPC-B like) 32 1,967 11.1 ms 46.9 ms 81 ms 136 ms 0
Read only 1 14,785 0.063 ms 0.091 ms 0.109 ms 0.142 ms 0
Read only 8 66,735 0.112 ms 0.202 ms 0.249 ms 0.331 ms 0
Read only 32 76,934 0.378 ms 0.627 ms 0.755 ms 0.983 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.82 s. 60 s per run, prepared statements. Latency comes from sampled transaction logs, and p99.9 is left out when fewer than 1,000 were sampled.

pgbench at scale 100

Workload Clients Transactions/s Median p95 p99 p99.9 Failed
Read/write (TPC-B like) 1 401 2.26 ms 3.23 ms 3.42 ms 15.3 ms 0
Read/write (TPC-B like) 8 1,460 4.35 ms 7.33 ms 49.1 ms 96.4 ms 0
Read/write (TPC-B like) 32 3,030 6.46 ms 16.1 ms 97.3 ms 274 ms 0
Read only 1 7,127 0.087 ms 0.124 ms 0.15 ms 0.988 ms 0
Read only 8 52,900 0.14 ms 0.256 ms 0.32 ms 0.752 ms 0
Read only 32 58,292 0.507 ms 0.825 ms 1.04 ms 2.12 ms 0

Scale 100 (10,000,000 accounts), loaded in 18.7 s. 60 s per run, prepared statements. Latency comes from sampled transaction logs, and p99.9 is left out when fewer than 1,000 were sampled.

MySQL

sysbench OLTP

Workload Threads Transactions/s Queries/s Median p95 p99 Errors
Read/write 1 104 2,084 9.39 ms 11.4 ms 18.6 ms 0
Read/write 8 392 7,844 18.6 ms 29.2 ms 51.9 ms 0
Read/write 32 815 16,299 29.2 ms 126 ms 223 ms 0
Read only 1 625 10,004 1.55 ms 1.89 ms 2.11 ms 0
Read only 8 2,705 43,275 2.81 ms 4.25 ms 5.47 ms 0
Read only 32 2,735 43,762 11.7 ms 14.5 ms 16.4 ms 0

10 tables of 100,000 rows, loaded in 13.3 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 80,063 72,784 0.767 ms 1.53 ms 2.11 ms
1:1 set:get 76,219 38,109 0.815 ms 1.56 ms 2.03 ms

1,000,000 keys of 32 bytes. 64 connections over 4 threads, 60 s per ratio.

Web frameworks

Framework Fortunes req/s Single query req/s JSON req/s Fortunes p99 at 256 connections
Next.js nextjs 896 3,168 4,254 414 ms
Express express-postgresjs 13,388 16,906 44,842 38.9 ms
Fastify fastify-postgres 13,699 18,354 50,359 39.7 ms
NestJS nestjs 6,494 7,283 25,996 61.2 ms
Nuxt nuxt 11,339 15,737 36,172 52.4 ms
FastAPI fastapi 5,095 7,136 27,651 236 ms
Django django-postgresql 3,005 3,202 7,542 211 ms
Rails rails 4,399 5,980 22,849 82.8 ms
Laravel laravel 1,303 1,320 2,452 209 ms
Symfony symfony 1,682 1,800 4,570 164 ms

Peak requests per second across the 64 and 256 connection levels, measured with wrk. Each test has to pass the TechEmpower response checks first, or it's marked invalid.

Web apps

WooCommerce

Page mix

Step Requests/s Median p95 p99 Error rate
8 virtual users
Home page 4.04 394 ms 504 ms 549 ms 0%
Shop page 4.04 528 ms 676 ms 742 ms 0%
Category page 4.04 344 ms 572 ms 678 ms 0%
Product page 4.04 369 ms 472 ms 515 ms 0%
Product search 4.04 313 ms 424 ms 471 ms 0%
32 virtual users
Home page 3.92 1.55 s 1.72 s 1.79 s 0%
Shop page 3.92 2.01 s 2.28 s 2.36 s 0%
Category page 3.92 1.66 s 2.13 s 2.28 s 0%
Product page 3.92 1.5 s 1.68 s 1.75 s 0%
Product search 3.92 1.35 s 1.53 s 1.63 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 7.64 415 ms 530 ms 569 ms 0%
Cart 7.64 349 ms 455 ms 482 ms 0%
Checkout 7.64 276 ms 370 ms 394 ms 0%
32 virtual users
Add to cart 7.44 1.57 s 1.86 s 1.92 s 0%
Cart 7.44 1.47 s 1.68 s 1.75 s 0%
Checkout 7.44 1.22 s 1.42 s 1.49 s 0%

k6 with a fixed number of virtual users, 61 to 65 s per level. The error rate counts responses that weren't a 200.

Discourse

Signed in

Step Requests/s Median p95 p99 Error rate
1 virtual user
Topic page 1.93 231 ms 255 ms 524 ms 0%
Topic JSON 0.973 119 ms 132 ms 149 ms 0%
Home page 0.973 208 ms 231 ms 297 ms 0%
Categories page 0.495 236 ms 295 ms 535 ms 0%
User activity page 0.478 137 ms 157 ms 317 ms 0%
4 virtual users
Topic page 6.94 248 ms 335 ms 675 ms 0%
Topic JSON 3.47 129 ms 165 ms 286 ms 0%
Home page 3.47 222 ms 293 ms 542 ms 0%
Categories page 1.74 257 ms 333 ms 387 ms 0%
User activity page 1.74 154 ms 281 ms 401 ms 0%
16 virtual users
Topic page 6.77 965 ms 1.17 s 1.71 s 0%
Topic JSON 3.4 734 ms 965 ms 1.31 s 0%
Home page 3.4 908 ms 1.12 s 1.62 s 0%
Categories page 1.72 987 ms 1.32 s 1.82 s 0%
User activity page 1.7 787 ms 948 ms 1.21 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 149 26.4 ms 51.4 ms 74.3 ms 0%
Topic JSON 74.7 24.3 ms 50.3 ms 79.6 ms 0%
Home page 74.6 26.5 ms 52.8 ms 85.9 ms 0%
Categories page 37.3 25.4 ms 50.9 ms 84.5 ms 0%
User activity page 37.4 159 ms 209 ms 362 ms 0%

k6 with a fixed number of virtual users, 60 to 61 s per level, after a 22 s warmup. The error rate counts responses that weren't a 200. Discourse ran with 8 app workers and 2048 MB of Postgres shared buffers, what its installer picks for a 8 GB box. Its installer adds no swap on a box this big. The container peaked at 2,697 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 7.76 38.2 ms 41.4 ms 45.4 ms 0%
Post page 19.4 19.5 ms 22.5 ms 29 ms 0%
Tag page 3.88 25.7 ms 28.8 ms 35.5 ms 0%
Author page 3.86 25.4 ms 27.7 ms 39 ms 0%
RSS feed 3.86 27.6 ms 35.9 ms 47.6 ms 0%
4 virtual users
Home page 8.96 123 ms 146 ms 160 ms 0%
Post page 22.4 80.5 ms 111 ms 127 ms 0%
Tag page 4.51 75 ms 98.9 ms 107 ms 0%
Author page 4.46 77.5 ms 99.2 ms 107 ms 0%
RSS feed 4.46 88 ms 116 ms 128 ms 0%
16 virtual users
Home page 8.85 462 ms 532 ms 555 ms 0%
Post page 22.2 380 ms 452 ms 485 ms 0%
Tag page 4.38 250 ms 316 ms 340 ms 0%
Author page 4.43 250 ms 326 ms 361 ms 0%
RSS feed 4.43 264 ms 314 ms 351 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 3.78 38 ms 42.6 ms 48 ms 0%
Post editor 11.3 14 ms 16.4 ms 19.6 ms 0%
Saving a draft 11.3 42 ms 47.2 ms 55 ms 0%
Member list 3.78 48.1 ms 56.1 ms 64.3 ms 0%
4 virtual users
Post list 4.94 48 ms 55.1 ms 59.3 ms 0%
Post editor 14.9 18.5 ms 27.1 ms 29.8 ms 0%
Saving a draft 14.9 208 ms 254 ms 270 ms 0%
Member list 4.99 58.9 ms 66.4 ms 80.7 ms 0%

k6 with a fixed number of virtual users, 60 s per level, after a 20 s warmup. The error rate counts responses that weren't a 200. Ghost ran the way its ghost-docker setup runs it: one Node process, and MySQL with its stock 128 MB buffer pool. Memory peaked with Ghost at 523 MB and MySQL at 624 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.5 88.2 ms 95.1 ms 99.3 ms 0%
Blog index 1.5 314 ms 331 ms 339 ms 0%
Blog post 4.47 27.5 ms 41.7 ms 44 ms 0%
Bread page 4.47 30.4 ms 32.9 ms 34.5 ms 0%
Location page 1.5 28.9 ms 32.3 ms 33.3 ms 0%
Site search 1.5 48.1 ms 82.9 ms 86.8 ms 0%
4 virtual users
Home page 2.46 233 ms 334 ms 359 ms 0%
Blog index 2.5 874 ms 1.2 s 1.23 s 0%
Blog post 7.41 61.4 ms 106 ms 150 ms 0%
Bread page 7.44 65.5 ms 103 ms 114 ms 0%
Location page 2.51 61.7 ms 102 ms 205 ms 0%
Site search 2.46 96.4 ms 228 ms 268 ms 0%
16 virtual users
Home page 3.04 607 ms 826 ms 984 ms 0%
Blog index 3.11 1.62 s 1.96 s 2.17 s 0%
Blog post 9.18 316 ms 574 ms 744 ms 0%
Bread page 9.2 335 ms 566 ms 802 ms 0%
Location page 3.11 324 ms 573 ms 733 ms 0%
Site search 3.04 384 ms 676 ms 786 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.559 95.8 ms 107 ms 125 ms 0%
Page explorer 1.15 418 ms 515 ms 604 ms 0%
Page editor 1.69 193 ms 231 ms 319 ms 0%
Image library 0.559 75.3 ms 130 ms 716 ms 0%
Admin page search 0.559 39.2 ms 86 ms 123 ms 0%
4 virtual users
Admin dashboard 0.817 335 ms 550 ms 617 ms 0%
Page explorer 1.68 1.24 s 2.42 s 3.06 s 0%
Page editor 2.52 430 ms 830 ms 914 ms 0%
Image library 0.85 254 ms 541 ms 553 ms 0%
Admin page search 0.817 94 ms 291 ms 332 ms 0%

k6 with a fixed number of virtual users, 60 to 61 s per level, after a 21 s warmup. The error rate counts responses that weren't a 200. Wagtail ran the way bakerydemo ships it: uWSGI with 2 workers of 4 threads each, whatever the box, and Postgres and Redis on stock settings. Memory peaked with Wagtail at 297 MB, Postgres at 151 MB, and Redis at 25 MB.

Advertised vs. measured

Advertised Measured
vCPU 4 4
CPU Shared vCPU 0% of busy CPU time stolen
RAM 8 GB 7.7 GiB
Storage 100 GB NVMe 96.8 GiB
Architecture x86_64 x86_64
Virtualization KVM KVM

Guests usually report slightly less RAM and disk than advertised because of kernel reservations and filesystem overhead.

Detected hardware

CPU model
Intel Core Processor (Broadwell, no TSX, IBRS)
CPU cores
4
CPU frequency
2600 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
7.7 GiB
Swap reported
0 MiB
Disk reported
96.8 GiB
Virtualization reported
KVM
CPU steal
0% of busy CPU time stolen
Distro
Ubuntu 24.04.5 LTS
Kernel
6.8.0-142-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
gp.starter
Product line
General Purpose
Location
Miami
vCPU
4 shared vCPU
Architecture
x86_64
RAM
8 GB
Storage
100 GB NVMe
Virtualization
KVM
Network
Unknown
Transfer
10 TB
Port 25
On request
Monthly price at test time
$15.21
Hourly price at test time
$0.021
YABS version
v2026-09-20
Ran at
Oct 17, 2026, 04:28:29 UTC
Parser version
5

Run timeline

Queued
Oct 17, 2026, 04:27:00 UTC
Server created
Oct 17, 2026, 04:28:25 UTC
First update from the server
Oct 17, 2026, 04:28:25 UTC
Completed
Oct 17, 2026, 06:10:29 UTC
Server deleted
Oct 17, 2026, 06:10:29 UTC
Cost of this run
$0.036
Watch party 0 watching

This party closed at . It's read only now.

Watch party

Loading the party