RunsOn m8i-flex.xlarge · EBS gp3 vs GitHub 4-core x64
RunsOn does each build for 7.8–8.5× less; on time, RunsOn is faster on the Rust build and neither is clearly faster on the TypeScript and Docker builds. Both 4 vCPU x64.
All three builds 8.0× cheaper on RunsOn: $0.0309 vs $0.2461RunsOn 1.1× faster: 16m 06s vs 17m 52s
Rust build 8.5× cheaper on RunsOn: $0.0054 vs $0.0457RunsOn 1.3× faster: 2m 49s vs 3m 38s
TypeScript build 8.2× cheaper on RunsOn: $0.0032 vs $0.0258within run-to-run spread: 1m 31s · 1m 44s
Docker build 7.8× cheaper on RunsOn: $0.0224 vs $0.1746within run-to-run spread: 11m 46s · 12m 30s
RunsOn m8i-flex.xlarge · EBS gp3
jobs ran from Amazon.com (US)
GitHub 4-core
jobs ran from Microsoft (US)
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 | GitHub | Gap |
|---|---|---|---|
| Cost | |||
| Cost per Rust build | $0.0054 | $0.0457 | 8.5× RunsOn |
| Cost per TypeScript build | $0.0032 | $0.0258 | 8.2× RunsOn |
| Cost per Docker build | $0.0224 | $0.1746 | 7.8× RunsOn |
| Price per minute | $0.0012 | $0.0120 | 9.7× RunsOn |
| Real builds, wall time | |||
| Rust build (spotify-player) | 2m 49s | 3m 38s | 1.3× RunsOn |
| TypeScript build (opencode) | 1m 31s | 1m 44s | ≈ even |
| Docker build (PostHog) | 11m 46s | 12m 30s | ≈ even |
| CPU & memory | |||
| PassMark single-thread (points) | 3,267 | 2,895 | 1.1× RunsOn |
| PassMark CPU Mark, all cores (points) | 8,030 | 7,511 | 1.1× RunsOn |
| sysbench CPU, 1 thread (events/s) | 3,054 | 4,076 | 1.3× GitHub |
| 7-Zip compression (MIPS) | 23,275 | 18,743 | 1.2× RunsOn |
| Memory read bandwidth | 21.8 GiB/s | 24.1 GiB/s | 1.1× GitHub |
| Measurement | RunsOn | GitHub | Gap |
|---|---|---|---|
| Workspace disk (fio) | |||
| Random read, 4k QD32 (IOPS) | 2,993 | 19,575 | 6.5× GitHub |
| Random write, 4k QD32 (IOPS) | 2,994 | 11,216 | 3.7× GitHub |
| Random read, 4k QD1 (IOPS) | 1,753 | 7,286 | 4.2× GitHub |
| QD1 read latency, p99 | 918 µs | 241 µs | 3.8× GitHub |
| Sequential read | 401 MiB/s | 394 MiB/s | ≈ even |
| Sequential write | 401 MiB/s | 244 MiB/s | 1.6× RunsOn |
| Sync write, 4k + fdatasync (IOPS) | 525 | 4,163 | 7.9× GitHub |
| Network, cache & Docker | |||
| Download from GitHub | 135 MiB/s | 95 MiB/s | 1.4× RunsOn |
| Cache restore, 4 GB (actions/cache) | 17s | 41s | 2.4× RunsOn |
| Cache save, 4 GB (actions/cache) | 14s | 34s | 2.4× RunsOn |
| docker pull | 6.0s | 16.4s | 2.7× RunsOn |
| Database | |||
| pgbench read/write (TPS) | 3,062 | 4,414 | 1.4× GitHub |
| pgbench read-only (TPS) | 55,039 | 40,172 | 1.4× RunsOn |
| Queue | |||
| Queue under burst load | 17s | 3s | 5.7× GitHub |
- ≈ 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); 3 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