Changes are coming to VPSBenchmarks in the next few weeks that will make it easier to find the VPS you need.
The new Best VPS rankings will no longer limit themselves to a month or a quarter of data, instead they are going to cover up to 12 months of tests. In addition the new rankings will be split into price ranges:
That means that in each ranking all products from all providers in the price range will be present, no more need to review current and past rankings to get the full picture. It also means that it will be an apple to apple comparison with all plans in the same ranking having a similar price.
There will be a new revision to each ranking every few months to keep them up-to-date.
The periodic emails will be updated as well to cover the new rankings when they get a new revision.
Since last year, we have been running a new type of test called "Web Runs". Those are controlled HTTP stress tests with varying rates of request. The HTTP requests are sent locally to a database heavy web application. During the test we measure latencies, maximum rate of requests and system metrics.
The "Web Runs" are going to replace the "Live Web" tests that were the first tests to ever run at vpsbenchmarks.com. The latter had the advantage of allowing remote timing measurements from various locations in the world, that will unfortunately no longer be possible so the Remote Timings metrics are going away.
But the "Live Web" test also came with several issues, not least that only a single VPS trial could run simultaneously. The "Live Web" tests also didn't allow controlling the rate of requests so it wasn't possible to determine the maximum load that the server could handle. "Web Runs" address all those issues.
With a new type of test come new metrics and changing metrics imply that the making of the grades is also changing. In particular, the Web Performance grade will now be made of "Web Runs" metrics instead of the "Live Web" metrics. But other grade categories are also changing: some metrics that were not very meaningful or were duplicates are removed (sysbench disk io latencies for example), some others are introduced (sysbench memory tests for example).
After the switch happens, the new grades will replace the old ones everywhere on the site for trials that have them (all trials after November 2019), others will still report the old grades.
In the Screener, only plans with the new grades will be included by default and plans will be ranked according to the new grades.
The new grades will become default in early May and the first Best VPS 2020 ranking is going to be published later that month. Stay tuned!
We are proud to provide objective and impartial benchmark data on this website. VPSBenchmarks receives support from some of the providers featured here but all tests are conducted the same way regardless of our relationships with them.
If you find our benchmarks valuable, you can help by making your cloud purchases using the Provider Affiliate Buttons displayed throughout the site.
All tests that were recently conducted at VpsBenchmarks: