Methodology
This page exposes online probes, real sample volume, reference baselines, coverage thresholds and current limitations so the source and boundaries of every data point can be inspected directly.
Current Measurement Framework
These are not static marketing statements. They describe the actual measurement and presentation rules used by the platform today.
Global Active Probing
Real probes launch requests from multiple geographies, covering mainland China and overseas regions instead of relying on a single network perspective.
Unified Sample Scope
Observation targets and aggregation rules are standardized across providers so results remain comparable.
Continuous Sampling & Aggregation
Samples are continuously written and aggregated by hour and region, while public pages read snapshots and aggregates for stable performance and consistent definitions.
Measured vs Claimed Layers
Security metrics are split between measured items and vendor-declared items so unverifiable claims do not pollute measured scores.
Probe Network Distribution
Current probe locations are distributed across the regions below. Coverage updates as more networks join the platform.
Show all 350 probesCollapse additional probes
Current Public Thresholds
Numeric metrics use a consistent measurement standard. Event counts, provider ownership and security evidence remain factual.
Security Score Notes
Measured Items:TLS 1.3, weak cipher suites, certificate chain integrity, HSTS, CSP, X-Content-Type-Options, HTTP/3 and OCSP Stapling.
Declared Items:Vendor-declared capabilities such as WAF or DDoS protection are shown separately as informational context instead of being mixed into measured scores.
Known limitations
- Node coverage is inferred from real probe observations and is not an official full node list from the vendor.
- The number of real probes is still limited, especially for multi-region coverage.
- Website speed tests and observation results can be affected by target-site volatility, throttling and temporary network jitter.
- Numeric dimensions without enough real samples use reference baselines; sample counts, ownership and security evidence remain factual.