Skip to main content

Scaleway BASIC3-X2C-4G

Paris 1

Benchmark complete
Finished Oct 11, 2026
Geekbench 7 single-core
2,189
Faster than 96% of 2 vCPU plans
Geekbench 7 multi-core
2,382
Faster than 68% of 2 vCPU plans
Disk 4K IOPS
5,142
fio random read and write, 50/50
Monthly price at test time
€28.80 EUR
71 multi-core points per dollar
Same price today

Server

  • Provider
    Scaleway
  • Plan
    BASIC3-X2C-4G
  • Location
    Paris 1
  • vCPU
    2
  • RAM
    4 GB
  • Storage
  • Network
    350 Mbps
  • OS image
    ubuntu_noble
  • Trigger
    Scheduled
  • Queued at
    Oct 11, 2026, 19:20:00 UTC
Visit Scaleway

CPU

Version Single-core Multi-core
Geekbench 7 2,189 2,382 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
2,042
3rd of 106
2,169
58th of 90
Navigation
1,820
7th of 106
Single-core only
HTML5 Browser
1,895
9th of 106
Single-core only
PDF Viewer
2,380
3rd of 106
Single-core only
Photo Library
2,305
3rd of 106
2,571
48th of 90
Clang
1,857
3rd of 106
1,977
66th of 90
Text Processing
2,137
3rd of 106
2,163
56th of 90
Asset Compression
2,205
3rd of 106
2,435
58th of 90
HDR
2,294
3rd of 106
2,530
45th of 90
Photo Editor
3,069
2nd of 106
3,685
34th of 90
Ray Tracer
1,797
3rd of 106
1,914
71st of 90
Structure from Motion
2,537
3rd of 106
Single-core only
Game Physics
2,078
3rd of 106
Single-core only
Video Encoder
2,187
3rd of 106
Single-core only
Audio Encoder
2,126
3rd of 106
Single-core only
Video Player
2,657
3rd of 106
Single-core only

Rank among the 106 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 97.2 GB/s 3 6.11%
Scale higher is better 88.7 GB/s 3 3.84%
Add higher is better 92.8 GB/s 3 5.64%
Triad higher is better 90.7 GB/s 3 4.31%

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 876/s 3 1.14%
RSA 4096 verifies higher is better 24,267/s 3 0.462%
SHA-256 higher is better 1.36 GB/s 3 1.29%
AES-256-GCM higher is better 23.1 GB/s 3 1.12%
ChaCha20-Poly1305 higher is better 6.06 GB/s 3 0.38%

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 6.46 ms 3 0.143%
Requests per second, 90th percentile higher is better 354/s 3 1.13%
Request latency, 99.9th percentile lower is better 15.6 ms 3 3.7%
Requests per second, average higher is better 350/s 3 0.732%

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

Disk

Block size Read Write Total
4K 10 MB/s (2,567 IOPS) 10.1 MB/s (2,575 IOPS) 20.1 MB/s (5,142 IOPS)
64K 125 MB/s (2,000 IOPS) 125.7 MB/s (2,010 IOPS) 250.7 MB/s (4,010 IOPS)
512K 120 MB/s (239 IOPS) 126.3 MB/s (252 IOPS) 246.3 MB/s (491 IOPS)
1M 118.3 MB/s (118 IOPS) 126.1 MB/s (126 IOPS) 244.4 MB/s (244 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 595 Mbps 5.39 Gbps
Eranium, Amsterdam, NL (100G) IPv4 602 Mbps 6.88 Gbps
Leaseweb, Singapore, SG (10G) IPv4 572 Mbps 1.4 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 559 Mbps 1.4 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 576 Mbps 3.01 Gbps

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 1,003 0.997 ms
fdatasync 1,013 0.987 ms
fsync 495 2.02 ms
fsync_writethrough Not supported here n/a
open_sync 473 2.11 ms
Two 8 kB writes
open_datasync 525 1.9 ms
fdatasync 977 1.02 ms
fsync 491 2.04 ms
fsync_writethrough Not supported here n/a
open_sync 226 4.43 ms
open_sync at different write sizes
1 * 16kB open_sync write 508 1.97 ms
2 * 8kB open_sync writes 251 3.98 ms
4 * 4kB open_sync writes 131 7.61 ms
8 * 2kB open_sync writes 58.2 17.2 ms
16 * 1kB open_sync writes 29.7 33.7 ms
fsync on a non-write descriptor
write, fsync, close 526 1.9 ms
write, close, fsync 505 1.98 ms
Non-synced 8 kB writes
write 2,936,094 0 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) 1 798 1.1 ms 1.87 ms 3.46 ms 7.03 ms 0
Read/write (TPC-B like) 8 1,932 2.84 ms 9.59 ms 16.7 ms 31.3 ms 0
Read/write (TPC-B like) 32 1,904 10.4 ms 49.4 ms 90.8 ms 241 ms 0
Read only 1 32,137 0.015 ms 0.027 ms 0.052 ms 4.52 ms 0
Read only 8 61,379 0.029 ms 0.127 ms 3.63 ms 13.6 ms 0
Read only 32 60,687 0.069 ms 1.28 ms 8.87 ms 26.4 ms 0

Scale 10 (1,000,000 accounts), loaded in 2.11 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) 1 526 1.43 ms 3.41 ms 9.24 ms 25 ms 0
Read/write (TPC-B like) 8 1,177 3.73 ms 18.4 ms 47.4 ms 244 ms 0
Read/write (TPC-B like) 32 1,698 13.2 ms 46.8 ms 77.8 ms 180 ms 0
Read only 1 17,575 0.017 ms 0.039 ms 0.131 ms 7.54 ms 0
Read only 8 45,669 0.036 ms 0.171 ms 4.6 ms 15.4 ms 0
Read only 32 43,984 0.097 ms 3.57 ms 11.9 ms 35.7 ms 0

Scale 100 (10,000,000 accounts), loaded in 39 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 1 115 2,300 6.91 ms 15.3 ms 57.9 ms 0
Read/write 8 275 5,504 21.1 ms 78.6 ms 121 ms 0
Read/write 32 454 9,083 53.9 ms 148 ms 227 ms 0
Read only 1 1,228 19,642 0.402 ms 4.82 ms 6.1 ms 0
Read only 8 2,169 34,696 1.08 ms 17.3 ms 29.7 ms 0
Read only 32 2,082 33,308 7.17 ms 74.5 ms 119 ms 0

10 tables of 100,000 rows, loaded in 15.8 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 68,719 62,471 0.383 ms 7.52 ms 14.7 ms
1:1 set:get 75,165 37,582 0.343 ms 7.23 ms 14.5 ms

1,000,000 keys of 32 bytes. 64 connections over 2 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 475 1,863 2,661 942 ms
Express express-postgresjs 6,768 10,876 41,123 68.8 ms
Fastify fastify-postgres 7,044 11,679 48,692 80.3 ms
NestJS nestjs 5,903 5,854 33,452 108 ms
Nuxt nuxt 5,999 11,207 45,762 109 ms
FastAPI fastapi 3,913 4,906 19,616 296 ms
Django django-postgresql 1,540 1,729 5,315 244 ms
Rails rails 2,743 3,922 21,285 240 ms
Laravel laravel 677 626 1,170 428 ms
Symfony symfony 767 821 2,668 391 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.

WooCommerce

Page mix

Step Requests/s Median p95 p99 Error rate
8 virtual users
Home page 1.64 931 ms 1.25 s 1.29 s 0%
Shop page 1.64 1.31 s 1.61 s 1.69 s 0%
Category page 1.64 840 ms 1.27 s 1.6 s 0%
Product page 1.64 938 ms 1.22 s 1.3 s 0%
Product search 1.64 778 ms 983 ms 1.05 s 0%
32 virtual users
Home page 1.77 3.58 s 4.2 s 4.66 s 0%
Shop page 1.77 4.79 s 5.9 s 6.1 s 0%
Category page 1.66 4.07 s 5.21 s 5.34 s 0%
Product page 1.36 3.72 s 4 s 4.12 s 0%
Product search 1.36 3.27 s 3.73 s 3.87 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 3.06 1.03 s 1.32 s 1.42 s 0%
Cart 3.06 856 ms 1.04 s 1.07 s 0%
Checkout 3.06 653 ms 804 ms 871 ms 0%
32 virtual users
Add to cart 3.27 3.3 s 4.2 s 4.55 s 0%
Cart 3.27 3.5 s 4.08 s 4.35 s 0%
Checkout 3.27 2.71 s 3.37 s 3.58 s 0%

k6 with a fixed number of virtual users, 63 to 71 s per level. The error rate counts responses that weren't a 200.

Discourse

Signed in

Skipped: not enough disk, needs 7394 MB and 4344 MB is free

Anonymous

Skipped: not enough disk, needs 7465 MB and 4344 MB is free

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 11 24.6 ms 31.7 ms 56.8 ms 0%
Post page 27.5 14 ms 20.6 ms 27.4 ms 0%
Tag page 5.5 16.2 ms 21.9 ms 31 ms 0%
Author page 5.5 17.1 ms 24.1 ms 34 ms 0%
RSS feed 5.5 18.3 ms 24.1 ms 31.1 ms 0%
4 virtual users
Home page 12.7 82.4 ms 108 ms 169 ms 0%
Post page 31.6 57.1 ms 82.1 ms 136 ms 0%
Tag page 6.36 51.4 ms 74.8 ms 101 ms 0%
Author page 6.32 54.3 ms 77.3 ms 107 ms 0%
RSS feed 6.32 53.3 ms 74.5 ms 89.5 ms 0%
16 virtual users
Home page 12 327 ms 459 ms 487 ms 0%
Post page 29.9 278 ms 402 ms 444 ms 0%
Tag page 5.97 179 ms 285 ms 323 ms 0%
Author page 5.98 179 ms 240 ms 321 ms 0%
RSS feed 5.95 182 ms 272 ms 327 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 4.32 31.3 ms 40.6 ms 47.6 ms 0%
Post editor 13 13.7 ms 23.2 ms 29.9 ms 0%
Saving a draft 13 35.4 ms 48.3 ms 90.8 ms 0%
Member list 4.34 34.5 ms 44.7 ms 53.6 ms 0%
4 virtual users
Post list 5.11 41.2 ms 54.7 ms 72.2 ms 0%
Post editor 15.4 20 ms 33.9 ms 47.8 ms 0%
Saving a draft 15.4 200 ms 258 ms 368 ms 0%
Member list 5.13 46.2 ms 59.1 ms 70.7 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 322 MB and MySQL at 624 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 2.2 56.2 ms 70 ms 78.3 ms 0%
Blog index 2.2 207 ms 229 ms 240 ms 0%
Blog post 6.56 19.8 ms 30.5 ms 35.4 ms 0%
Bread page 6.58 21.1 ms 28.9 ms 34.1 ms 0%
Location page 2.2 20.4 ms 31.5 ms 36.6 ms 0%
Site search 2.18 34.3 ms 57.1 ms 64.8 ms 0%
4 virtual users
Home page 2.51 225 ms 321 ms 422 ms 0%
Blog index 2.54 769 ms 960 ms 1.03 s 0%
Blog post 7.52 65.4 ms 113 ms 194 ms 0%
Bread page 7.55 70.1 ms 107 ms 125 ms 0%
Location page 2.54 69.7 ms 99.2 ms 111 ms 0%
Site search 2.51 100 ms 230 ms 252 ms 0%
16 virtual users
Home page 2.53 746 ms 993 ms 1.09 s 0%
Blog index 2.56 1.81 s 2.16 s 2.31 s 0%
Blog post 7.59 422 ms 667 ms 775 ms 0%
Bread page 7.59 445 ms 650 ms 763 ms 0%
Location page 2.53 433 ms 645 ms 781 ms 0%
Site search 2.53 528 ms 763 ms 842 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 1.11 60.6 ms 78.6 ms 136 ms 0%
Page explorer 2.24 197 ms 229 ms 361 ms 0%
Page editor 3.35 104 ms 136 ms 177 ms 0%
Image library 1.11 42.2 ms 61.2 ms 267 ms 0%
Admin page search 1.11 26.7 ms 52.1 ms 59.3 ms 0%
4 virtual users
Admin dashboard 1.13 283 ms 513 ms 531 ms 0%
Page explorer 2.27 868 ms 1.2 s 1.31 s 0%
Page editor 3.43 390 ms 645 ms 755 ms 0%
Image library 1.14 221 ms 428 ms 470 ms 0%
Admin page search 1.14 107 ms 315 ms 371 ms 0%

k6 with a fixed number of virtual users, 60 to 61 s per level, after a 20 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 295 MB, Postgres at 147 MB, and Redis at 8 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 37.5% of busy CPU time stolen
RAM 4 GB 3.8 GiB
Storage 8.9 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
AMD EPYC 9555P 64-Core Processor
CPU cores
2
CPU frequency
3200 MHz
AES-NI
Yes
VM-x/AMD-V
Yes
RAM reported
3.8 GiB
Swap reported
0 MiB
Disk reported
8.9 GiB
Virtualization reported
KVM
CPU steal
37.5% 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
No

Advertised at test time

Plan
BASIC3-X2C-4G
Product line
General Purpose
Location
Paris 1
vCPU
2 shared vCPU
Architecture
x86_64
RAM
4 GB
Storage
Virtualization
KVM
Network
350 Mbps
Transfer
Unmetered
Port 25
Unknown
Monthly price at test time
€28.80 EUR
Hourly price at test time
€0.039 EUR
YABS version
v2026-09-20
Ran at
Oct 11, 2026, 19:20:50 UTC
Parser version
5

Run timeline

Queued
Oct 11, 2026, 19:20:00 UTC
Server created
Oct 11, 2026, 19:20:44 UTC
First update from the server
Oct 11, 2026, 19:20:44 UTC
Completed
Oct 11, 2026, 20:53:00 UTC
Server deleted
Oct 11, 2026, 20:53:00 UTC
Cost of this run
€0.061 EUR
Watch party 0 watching

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

Watch party

Loading the party