Methodology
Benchmark methodology
How Cloud Provider Benchmarks measures compute, storage, network, Kubernetes, GPU inference, audit logging and pricing: tools, procedures and publication rules.
Principles that apply to every benchmark
- Identical procedure, tool versions and workload parameters for every provider in a comparison.
- Raw output is stored with each result; derived metrics are recomputed from it.
- Every result enters as pending verification and is published only after an independent re-run within tolerance.
- Instance type, region, image, kernel and driver versions are recorded with every run.
- Providers are not notified before testing and cannot edit results; factual corrections follow the editorial policy.
- Derived values (from specifications or price lists) are labelled as such and never presented as measurements.
-
Compute benchmark methodology
How CPU single-thread and multi-thread throughput, memory bandwidth and provisioning time are measured on cloud virtual machines, and how results are verified.
v1.0 · 6 November 2026
-
Block storage benchmark methodology
How random and sequential IOPS, throughput and tail latency of cloud block volumes are measured with fio, including volume sizing, preconditioning and verification.
v1.0 · 6 November 2026
-
Network benchmark methodology
How intra-region TCP throughput and round-trip latency between cloud instances, and latency to major Turkish and European cities, are measured with iperf3 and mtr.
v1.0 · 6 November 2026
-
Object storage benchmark methodology
How S3-compatible object storage GET and PUT throughput and small-object latency are measured with MinIO warp from an instance in the same region.
v1.0 · 6 November 2026
-
Managed Kubernetes benchmark methodology
How managed Kubernetes cluster creation time, node join time and conformance are measured with the provider API, kube-burner and Sonobuoy.
v1.0 · 6 November 2026
-
GPU and LLM inference benchmark methodology
How LLM inference is measured on H100, H200 and L40S with vLLM: models, precisions, context and concurrency scenarios, metrics, feasibility rules and verification.
v1.0 · 6 November 2026
-
Cloud security and audit logging methodology
How cloud audit-logging and security capabilities are assessed from documentation using qualitative values, feature definitions and the conceptual audit event model.
v1.0 · 6 November 2026
-
Pricing data and price-performance methodology
How cloud list prices are collected, normalised to vCPU-hour, GB-hour and GPU-hour, kept in original currencies, and combined with benchmark results.
v1.0 · 6 November 2026