quickstart →

RunsOn m8id.xlarge · local NVMe vs Blacksmith 4 vCPU x64

RunsOn does each build for 2.1–3.4× less; on time, Blacksmith is faster on the Docker build and neither is clearly faster on the Rust and TypeScript builds. Both 4 vCPU x64.

All three builds 2.3× cheaper on RunsOn: $0.0316 vs $0.0741Blacksmith 1.6× faster: 8m 27s vs 13m 19s
Rust build 2.1× cheaper on RunsOn: $0.0074 vs $0.0155within run-to-run spread: 2m 44s · 1m 47s
TypeScript build 3.4× cheaper on RunsOn: $0.0035 vs $0.0121within run-to-run spread: 1m 20s · 1m 19s
Docker build 2.3× cheaper on RunsOn: $0.0206 vs $0.0465Blacksmith 1.7× faster: 5m 22s vs 9m 15s

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 $0.0074 $0.0155 2.1× RunsOn
Cost per TypeScript build $0.0035 $0.0121 3.4× RunsOn
Cost per Docker build $0.0206 $0.0465 2.3× RunsOn
Price per minute $0.0016 $0.0080 4.9× RunsOn
Real builds, wall time
Rust build (spotify-⁠player) 2m 44s 1m 47s ≈ even
TypeScript build (opencode) 1m 20s 1m 19s ≈ even
Docker build (PostHog) 9m 15s 5m 22s 1.7× Blacksmith
CPU & memory
PassMark single-⁠thread (points) 3,264 4,332 1.3× Blacksmith
PassMark CPU Mark, all cores (points) 8,033 14,771 1.8× Blacksmith
sysbench CPU, 1 thread (events/s) 3,079 6,493 2.1× Blacksmith
7-⁠Zip compression (MIPS) 24,076 28,802 1.2× Blacksmith
Memory read bandwidth 21.7 GiB/s 41.7 GiB/s 1.9× Blacksmith
Measurement RunsOn Blacksmith Gap
Workspace disk (fio)
Random read, 4k QD32 (IOPS) 67,090 728,035 10.9× Blacksmith
Random write, 4k QD32 (IOPS) 33,526 218,915 6.5× Blacksmith
Random read, 4k QD1 (IOPS) 10,866 71,728 6.6× Blacksmith
QD1 read latency, p99 249 µs 16 µs 15.6× Blacksmith
Sequential read 451 MiB/s 7.0 GiB/s 16.0× Blacksmith
Sequential write 216 MiB/s 1.7 GiB/s 8.0× Blacksmith
Sync write, 4k + fdatasync (IOPS) 7,903 17,925 2.3× Blacksmith
Network, cache & Docker
Download from GitHub 187 MiB/s 76 MiB/s 2.5× RunsOn
Cache restore, 4 GB (actions/cache) 30s 11s 2.7× Blacksmith
Cache save, 4 GB (actions/cache) 24s 7s 3.7× Blacksmith
docker pull 5.7s 7.9s 1.4× RunsOn
Database
pgbench read/write (TPS) 7,066 12,408 1.8× Blacksmith
pgbench read-⁠only (TPS) 60,641 109,979 1.8× Blacksmith
Queue
Queue under burst load 19s 10s 1.9× 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); 5 of its jobs fell back to on-demand (AWS had no spot capacity for the type) and are priced at the spot rate over the same billed time
  • 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