quickstart →

RunsOn m8azn.xlarge · gp3 1000 MiB/s vs Blacksmith 4 vCPU x64

RunsOn does each build for 1.2–2.0× less; neither is clearly faster (within 5% or inside each other's run-to-run range). Both 4 vCPU x64.

All three builds 1.3× cheaper on RunsOn: $0.0568 vs $0.0741Blacksmith 1.1× faster: 8m 27s vs 9m 33s
Rust build 1.5× cheaper on RunsOn: $0.0104 vs $0.0155within run-to-run spread: 1m 41s · 1m 47s
TypeScript build 2.0× cheaper on RunsOn: $0.0060 vs $0.0121within run-to-run spread: 47s · 1m 19s
Docker build 1.2× cheaper on RunsOn: $0.0404 vs $0.0465within run-to-run spread: 7m 05s · 5m 22s

Side by side

Every measurement both runners share, cost first. The dot marks the better value; gap is the larger over the smaller.

Measurement RunsOn Blacksmith Gap
Cost
Cost per Rust build $0.0104 $0.0155 1.5× RunsOn
Cost per TypeScript build $0.0060 $0.0121 2.0× RunsOn
Cost per Docker build $0.0404 $0.0465 1.2× RunsOn
Price per minute $0.0045 $0.0080 1.8× RunsOn
Real builds, wall time
Rust build (spotify-⁠player) 1m 41s 1m 47s ≈ even
TypeScript build (opencode) 47s 1m 19s ≈ even
Docker build (PostHog) 7m 05s 5m 22s ≈ even
CPU & memory
PassMark single-⁠thread (points) 4,260 4,332 ≈ even
PassMark CPU Mark, all cores (points) 15,109 14,771 ≈ even
sysbench CPU, 1 thread (events/s) 5,619 6,493 1.2× Blacksmith
7-⁠Zip compression (MIPS) 42,321 28,802 1.5× RunsOn
Memory read bandwidth 41.0 GiB/s 41.7 GiB/s ≈ even
Measurement RunsOn Blacksmith Gap
Workspace disk (fio)
Random read, 4k QD32 (IOPS) 15,994 728,035 45.5× Blacksmith
Random write, 4k QD32 (IOPS) 15,991 218,915 13.7× Blacksmith
Random read, 4k QD1 (IOPS) 1,772 71,728 40.5× Blacksmith
QD1 read latency, p99 799 µs 16 µs 50.2× Blacksmith
Sequential read 1,001 MiB/s 7.0 GiB/s 7.2× Blacksmith
Sequential write 1,001 MiB/s 1.7 GiB/s 1.7× Blacksmith
Sync write, 4k + fdatasync (IOPS) 541 17,925 33.1× Blacksmith
Network, cache & Docker
Download from GitHub 172 MiB/s 76 MiB/s 2.3× RunsOn
Cache restore, 4 GB (actions/cache) 7s 11s 1.6× RunsOn
Cache save, 4 GB (actions/cache) 9s 7s 1.4× Blacksmith
docker pull 4.6s 7.9s 1.7× RunsOn
Database
pgbench read/write (TPS) 3,741 12,408 3.3× Blacksmith
pgbench read-⁠only (TPS) 164,328 109,979 1.5× RunsOn
Queue
Queue under burst load 17s 10s 1.6× Blacksmith
  • ≈ even: under 5% apart, or a build inside both runners' run-to-run spread
  • Queue: identical jobs queued at the same instant (burst suite)
  • RunsOn at EC2 spot, its default (7-day average of the cheapest us-east-1 zone's spot price, fetched 16 Nov 2026); its jobs ran on spot
  • Cost: a managed SaaS runner against RunsOn self-hosted on your AWS account; the effort of running it was not measured

Other head-to-heads