Every Time I Run DNS Benchmark I Get Different Conclusions

  • DNS Benchmark v2 is Finished and Available!
    Guest:
    That's right. It took an entire year, but the result far more accurate and feature laden than we originally planned. The world now has a universal, multi-protocol, super-accurate, DNS resolver performance-measuring tool. This major second version is not free. But the deal is, purchase it once for $9.95 and you own it — and it's entire future — without ever being asked to pay anything more. For an overview list of features and more, please see The DNS Benchmark page at GRC. If you decide to make it your own, thanks in advance. It's a piece of work I'm proud to offer for sale. And if you should have any questions, many of the people who have been using and testing it throughout the past year often hang out here.
    /Steve.
  • Be sure to checkout “Tips & Tricks”
    Dear Guest Visitor → Once you register and log-in please checkout the “Tips & Tricks” page for some very handy tips!

    /Steve.

  • BootAble – FreeDOS boot testing freeware

    To obtain direct, low-level access to a system's mass storage drives, SpinRite runs under a GRC-customized version of FreeDOS which has been modified to add compatibility with all file systems. In order to run SpinRite it must first be possible to boot FreeDOS.

    GRC's “BootAble” freeware allows anyone to easily create BIOS-bootable media in order to workout and confirm the details of getting a machine to boot FreeDOS through a BIOS. Once the means of doing that has been determined, the media created by SpinRite can be booted and run in the same way.

    The participants here, who have taken the time to share their knowledge and experience, their successes and some frustrations with booting their computers into FreeDOS, have created a valuable knowledgebase which will benefit everyone who follows.

    You may click on the image to the right to obtain your own copy of BootAble. Then use the knowledge and experience documented here to boot your computer(s) into FreeDOS. And please do not hesitate to ask questions – nowhere else can better answers be found.

    (You may permanently close this reminder with the 'X' in the upper right.)

jefred

jefred

Member
Dec 22, 2025
9
0
Every time I run DNS Benchmark Version 2, Release 4, I get a different report called “Conclusions”. I’m not exactly sure why this is happening. My router is an ASUS RT-AX88U Pro. This is what I suspect (but I could be wrong): The way that I have my IPv6 configured but it is showing under “Tabular Data” that all my numbers look correct. No matter what changes I make and I get the following response or “Conclusions”.

System nameservers are SLOWER than 31 public alternatives! This benchmark found 31 publicly available DNS nameservers that are statistically significantly faster than the slowest nameserver currently being used by this system. If you were to adjust your system's configuration to use the faster of these nameservers instead of what it is currently using, your DNS lookup performance, and all use of the Internet, would be improved.

The addresses of the 31 significantly faster publicly available DNS nameservers, listed in order of declining speed (the fastest is first), are:

Code: 
2606:4700:4700::1001
9.9.9.9
1.1.1.1
2620: fe:: fe
1.0.0.1
2620: fe:: fe: 10
198.6.1.122
2606:4700:4700::1111
208.67.220.220
2620: fe::10
208.67.220.123
67.17.215.132
4.2.2.1
209.244.0.3
198.153.192.1
206.165.6.11
156.154.71.1
4.2.2.6
4.2.2.4
129.250.35.251
129.250.35.250
209.130.139.2
66.109.229.4
8.8.4.4
204.95.160.2
209.244.0.4
12.127.16.67
206.165.6.12
208.67.222.222
209.18.47.62
8.8.8.8

Note: A total of 35 publicly available nameservers are on average faster than the slowest nameserver being used by this system, but the speed difference is only statistically significant for 31 of them shown above.

Right now I have my DNS Server set to “DNS Server: 129.250.35.251, 129.250.35.250” When I changed it to DNS Server: 1.0.0.1, 1.1.1.1” I had a similar conclusion even though my DNS server numbers were near the top.

And just to make this clear: When I’m changing my DNS server addresses I always make sure that I update my router so the numbers are taking and are not changing.

I’m not sure if I’m doing something wrong or something else is going on but it’s very frustrating. Any help you can give me would be greatly appreciated. Thanks in advance, Jefred
 
I just changed my DNS settings back to Cloudflare (1.1.1.1 & 1.0.0.1). I ran the test again and this is the report that I got back:

System nameservers are SLOWER than 4 public alternatives!
This benchmark found 4 publicly available DNS nameservers that are statistically significantly faster than the slowest nameserver currently being used by this system. If you were to adjust your system's configuration to use the faster of these nameservers instead of what it is currently using, your DNS lookup performance, and all use of the Internet, would be improved.

The addresses of the 4 significantly faster publicly available DNS nameservers, listed in order of declining speed (the fastest is first), are:

Code: 
 129.250.35.251
 1.1.1.1
 1.0.0.1
 156.154.71.1

Note: A total of 4 publicly available nameservers are on average faster than the slowest nameserver being used by this system, but the speed difference is only statistically significant for 4 of them shown above.

It's interesting to note that the "4 significantly faster publicly available DNS nameservers" are actually my DNS Server settings (1.1.1.1 & 1.0.0.1). I don't know why I'm getting these reports but I think that this is about as good as it's going to get, however I'm just a little perplexed as to why I'm getting these reports or conclusions. I have ran the test many times. When I first ran it, I ran the comprehensive analysis that it say's you only need to run once. Then I ran the Benchmarks about 5 or 6 times on the 5x setting. My webpages are loading faster now.
 
Last edited by a moderator:
Hi @jefred,

One of the things we learned through the development of v2 is that there is so much variation in packet-transit timing on today's Internet that a great many more samples need to be taken to obtain statistical significance — and repeatability. As such, the Benchmark's standard default 5x sample size represents a time vs consistency compromise. Taking more samples will produce a superior result when you can spare the time to take them.

Those “old school” 129.250.35.251 and 129.250.35.250 resolvers have remained solid choices, and I've been interested to see that they still rank highly. And, of course the 1.1.1.1 and 1.0.0.1 pair are also good choices for you, as we see in the lineup you posted.

The question of what resolvers your system is actually using is answered by which resolvers are encircled by the black rectangle. One way to see for sure, is to turn off sorting with the checkbox at the left of the Nameserver's tab. Or you could right-click on the resolver's list and chose to "Pin system resolvers to the top", which would lock your system's resolvers to the top of the list and show that they are pinned with a blue encircling highlight.

Remember that the Conclusions tab is saying that those resolvers listed are faster than your SLOWEST system resolver. So if you have a third resolver that's not up to par, that could be causing those conclusions.
 
jefred said:
It's interesting to note that the "4 significantly faster publicly available DNS nameservers" are actually my DNS Server settings (1.1.1.1 & 1.0.0.1). I don't know why I'm getting these reports but I think that this is about as good as it's going to get, however I'm just a little perplexed as to why I'm getting these reports or conclusions.
Click to expand...
Okay... so what resolvers are showing encircled in black when you run the Benchmark??

IF you've been setting your router to BE your network's DNS, and your router is naming itself as your system's resolver, then that would match and explain what you're seeing. It's doing a better job than it was. But the Benchmark is saying that if you were to MANUALLY configure your system with 1.1.1.1 and 1.0.0.1 directly, instead of (I guess?) relying on DHCP which is causing your machine to rely upon the router, THEN you'd be golden.

(Unfortunately, I must get to work on tomorrow's podcast. I'll check back later, or I'm sure others who are knowledgeable will show up to continue offering some thoughts.)
 
jefred said:
Right now I have my DNS Server set to “DNS Server: 129.250.35.251, 129.250.35.250” When I changed it to DNS Server: 1.0.0.1, 1.1.1.1” I had a similar conclusion even though my DNS server numbers were near the top.

And just to make this clear: When I’m changing my DNS server addresses I always make sure that I update my router so the numbers are taking and are not changing.
Click to expand...
Whilst you may be setting your DNS server/router to be 129.250.35.251, 129.250.35.250, what does you PC show? It may be using the router as the primary DNS server. On Windows, run "ipconfig/all" from a command prompt. That should show what you PC is actually using. DNSB should confirm this by showing a black box around the system DNS servers, check is 192.168.x.x is in there - that will be your router.
 
AlanD said:
Whilst you may be setting your DNS server/router to be 129.250.35.251, 129.250.35.250, what does you PC show? It may be using the router as the primary DNS server. On Windows, run "ipconfig/all" from a command prompt. That should show what you PC is actually using. DNSB should confirm this by showing a black box around the system DNS servers, check is 192.168.x.x is in there - that will be your router.
Click to expand...
Okay... so what resolvers are showing encircled in black when you run the Benchmark??

192.168.50.1 - First one - My router (Default Gateway)
2603:8000:102:b9b::1 - Second one
 
peterblaise said:
@jefred, why the spaces in:

2620: fe:: fe

2620: fe:: fe: 10

2620: fe::10

?

Thanks.
Click to expand...
This one 2603:8000:102:b9b::1 is actually my IPv6 Internet Protocol

This is what it is showing from the command prompt (ipconfig /all)

DNS Servers . . . . . . . . . . . : 2603:8000:102:b9b::1
192.168.50.1
2603:8000:102:b9b::1

Sorry about the confusion.
 
jefred said:
Okay... so what resolvers are showing encircled in black when you run the Benchmark??

192.168.50.1 - First one - My router (Default Gateway)
2603:8000:102:b9b::1 - Second one
Click to expand...
That may be why DNSB is advising that there are 4 faster DNS servers than your current settings.

Whilst your router may be using the fastest ones, your PC is going to the router first and then out to the selected servers. Going direct from the PC would be faster.
 
jefred said:
In regards' to the spaces I was just clicking and pasting and that is how they came up.
Click to expand...
Those spaces render those IPv6 addresses unusable. Please remove the spaces.

R76 (and now R77) will tolerate those malformed addresses but will not be able to use them.
 
jefred said:
In regards' to the spaces I was just clicking and pasting and that is how they came up. I think I have a picture if you want to see what I mean?
Click to expand...

Yeah, what shows one thing but copies another?!?

I used INI files saved by DNSBench and then Notepad shows perfect
formatting:

192.168.50.1 Non-routable local internet address
2603:8000:102:b9b::1 syn-2603-8000-0102-0b9b-0000-0000-0000-0001.res6.spectrum.com

But even IPCONFIG at a command prompt let's me copy and paste
full contents, no letters or numbers missing.

What's goofing on your screen?!?

Thanks.
 
Last edited:
This is what I get when I use the syntax IPCONFIG at a command prompt:

Code: 
Wireless LAN adapter Wi-Fi:

   Connection-specific DNS Suffix  . :
   IPv6 Address. . . . . . . . . . . : 2603:8000:102:b9b:20fc:e02b:ed0b:c513
   Temporary IPv6 Address. . . . . . : 2603:8000:102:b9b:8494:15f2:ebc:130f
   Link-local IPv6 Address . . . . . : fe80::73b1:d52:68b7:fbc0%17
   IPv4 Address. . . . . . . . . . . : 192.168.50.138
   Subnet Mask . . . . . . . . . . . : 255.255.255.0
   Default Gateway . . . . . . . . . : fe80::ca7f:54ff:feb5:dc08%17
                                       192.168.50.1

And this is what I get when I use the syntax ipconfig/all at a command prompt:

Code: 
Wireless LAN adapter Wi-Fi:

   Connection-specific DNS Suffix  . :
   Description . . . . . . . . . . . : Intel(R) Wi-Fi 6E AX211 160MHz
   Physical Address. . . . . . . . . : 64-49-7D-83-13-78
   DHCP Enabled. . . . . . . . . . . : Yes
   Autoconfiguration Enabled . . . . : Yes
   IPv6 Address. . . . . . . . . . . : 2603:8000:102:b9b:20fc:e02b:ed0b:c513(Preferred)
   Temporary IPv6 Address. . . . . . : 2603:8000:102:b9b:8494:15f2:ebc:130f(Preferred)
   Link-local IPv6 Address . . . . . : fe80::73b1:d52:68b7:fbc0%17(Preferred)
   IPv4 Address. . . . . . . . . . . : 192.168.50.138(Preferred)
   Subnet Mask . . . . . . . . . . . : 255.255.255.0
   Lease Obtained. . . . . . . . . . : Tuesday, December 23, 2025 10:54:03 AM
   Lease Expires . . . . . . . . . . : Wednesday, December 24, 2025 10:54:14 PM
   Default Gateway . . . . . . . . . : fe80::ca7f:54ff:feb5:dc08%17
                                       192.168.50.1
   DHCP Server . . . . . . . . . . . : 192.168.50.1
   DHCPv6 IAID . . . . . . . . . . . : 409225597
   DHCPv6 Client DUID. . . . . . . . : 00-01-00-01-2F-9A-76-11-E8-80-88-A0-CE-1A
   DNS Servers . . . . . . . . . . . : 2603:8000:102:b9b::1
                                       192.168.50.1
                                       2603:8000:102:b9b::1
   NetBIOS over Tcpip. . . . . . . . : Enabled
 
peterblaise said:
Yeah, what shows one thing but copies another?!?

I used INI files saved by DNSBench and then Notepad shows perfect
formatting:

192.168.50.1 Non-routable local internet address
2603:8000:102:b9b::1 syn-2603-8000-0102-0b9b-0000-0000-0000-0001.res6.spectrum.com

But even IPCONFIG at a command prompt let's me copy and paste
full contents, no letters or numbers missing.

What's goofing on your screen?!?

Thanks.
Click to expand...
I think it was just a formatting issue when I copied it from the DNS Benchmark screen. It has not happened again.
 
OK, your IPCONFIG produces this INI file through DNSBench 2 for me:

192.168.50.1 Non-routable local internet address
192.168.50.138 Non-routable local internet address
255.255.255.0 ··· no official Internet DNS name ···
2603:8000:102:b9b::1 syn-2603-8000-0102-0b9b-0000-0000-0000-0001.res6.spectrum.com
2603:8000:102:b9b:20fc:e02b:ed0b:c513 syn-2603-8000-0102-0b9b-20fc-e02b-ed0b-c513.res6.spectrum.com
2603:8000:102:b9b:8494:15f2:ebc:130f syn-2603-8000-0102-0b9b-8494-15f2-0ebc-130f.res6.spectrum.com

... all red and dead:

"DNS queries are not answered at this IP."

Everything's different for everyone everywhere, hence the need to test
ourselves, so to speak.

- - - - -

Back to your inquiry: why different every time?

Because ... it's the Internet.

We have no control.

But DNSBench will help us compare and narrow our choices.

I'm down to ~100 DNS servers that I'm perpetually comparing.

And, like you, they re-rank differently each test.

So on the one hand, what the heck?!?

On the other hand, I guess my ~100 are pretty well-chosen and
equivalent, good for me.

Here's a recent Tabular Data of my System DNS servers at
the moment, best to worst:

75. 75. 75. 75 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.010 | 0.035 | 0.277 | 0.012 | 0.343 |
- Cached Name | 0.010 | 0.014 | 0.023 | 0.002 | 0.143 |
- Uncached Name | 0.019 | 0.065 | 0.277 | 0.071 | 1.092 |
- DotCom Lookup | 0.019 | 0.028 | 0.041 | 0.007 | 0.250 |
---<-------->---+-------+-------+-------+-------+-------+
cdns01.comcast.net
COMCAST CABLE COMMUNICATIONS INC.

. . .

75. 75. 76. 76 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.023 | 0.058 | 0.295 | 0.017 | 0.293 |
- Cached Name | 0.023 | 0.028 | 0.031 | 0.001 | 0.036 |
- Uncached Name | 0.029 | 0.098 | 0.295 | 0.079 | 0.806 |
- DotCom Lookup | 0.031 | 0.049 | 0.069 | 0.009 | 0.184 |
---<-------->---+-------+-------+-------+-------+-------+
cdns02.comcast.net
COMCAST CABLE COMMUNICATIONS INC.

Average average is 0.035 to 0.058 milliseconds in the above results.

All essentially equivalent, and responsive, so in this case, I'm using
DNSBench to CONFIRM that I'm getting what I'm paying for.

And that's a good thing.

Now I can compare to my ~100 good / better / best and see if the
milliseconds differences matter or not - another terrific piece of
CONFIRMATION provided by DNSBench.

Here's the top resolver - note the average average milliseconds
peak at 0.024 - nice:

1. 1. 1. 1 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.009 | 0.024 | 0.260 | 0.006 | 0.250 |
- Cached Name | 0.009 | 0.013 | 0.020 | 0.002 | 0.154 |
- Uncached Name | 0.014 | 0.044 | 0.260 | 0.062 | 1.409 |
- DotCom Lookup | 0.015 | 0.017 | 0.024 | 0.002 | 0.118 |
---<-------->---+-------+-------+-------+-------+-------+
one.one.one.one
APNIC AND CLOUDFLARE DNS RESOLVER PROJECT

... and so on.

A fastest test of 0.024 milliseconds compared to my System's fastest
test of 0.035 milliseconds means ... what?

I dunno, yet.

I get to study tons of results like that, and start swapping DNS servers
into my System and see how things feel.

And test again, and again, as well as confirm via all the Internet speed
tests out there.

Busy, busy, busy.

Are we having fun yet?

;-)

- - - - -

So, back to you, across your various DNSBench Benchmark results
in Tabular Data, what's your average average millisecond range from
worst System to best possible tested alternative?

And again, after a few 5x and longer Benchmarks next month?

It's what we do.

Thanks.
 
Last edited:
peterblaise said:
OK, your IPCONFIG produces this INI file through DNSBench 2 for me:

192.168.50.1 Non-routable local internet address
192.168.50.138 Non-routable local internet address
255.255.255.0 ··· no official Internet DNS name ···
2603:8000:102:b9b::1 syn-2603-8000-0102-0b9b-0000-0000-0000-0001.res6.spectrum.com
2603:8000:102:b9b:20fc:e02b:ed0b:c513 syn-2603-8000-0102-0b9b-20fc-e02b-ed0b-c513.res6.spectrum.com
2603:8000:102:b9b:8494:15f2:ebc:130f syn-2603-8000-0102-0b9b-8494-15f2-0ebc-130f.res6.spectrum.com

... all red and dead:

"DNS queries are not answered at this IP."

Everything's different for everyone everywhere, hence the need to test
ourselves, so to speak.

- - - - -

Back to your inquiry: why different every time?

Because ... it's the Internet.

We have no control.

But DNSBench will help us compare and narrow our choices.

I'm down to ~100 DNS servers that I'm perpetually comparing.

And, like you, they re-rank differently each test.

So on the one hand, what the heck?!?

On the other hand, I guess my ~100 are pretty well-chosen and
equivalent, good for me.

Here's a recent Tabular Data of my System DNS servers at
the moment, best to worst:

75. 75. 75. 75 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.010 | 0.035 | 0.277 | 0.012 | 0.343 |
- Cached Name | 0.010 | 0.014 | 0.023 | 0.002 | 0.143 |
- Uncached Name | 0.019 | 0.065 | 0.277 | 0.071 | 1.092 |
- DotCom Lookup | 0.019 | 0.028 | 0.041 | 0.007 | 0.250 |
---<-------->---+-------+-------+-------+-------+-------+
cdns01.comcast.net
COMCAST CABLE COMMUNICATIONS INC.

. . .

75. 75. 76. 76 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.023 | 0.058 | 0.295 | 0.017 | 0.293 |
- Cached Name | 0.023 | 0.028 | 0.031 | 0.001 | 0.036 |
- Uncached Name | 0.029 | 0.098 | 0.295 | 0.079 | 0.806 |
- DotCom Lookup | 0.031 | 0.049 | 0.069 | 0.009 | 0.184 |
---<-------->---+-------+-------+-------+-------+-------+
cdns02.comcast.net
COMCAST CABLE COMMUNICATIONS INC.

Average average is 0.035 to 0.058 milliseconds in the above results.

All essentially equivalent, and responsive, so in this case, I'm using
DNSBench to CONFIRM that I'm getting what I'm paying for.

And that's a good thing.

Now I can compare to my ~100 good / better / best and see if the
milliseconds differences matter or not - another terrific piece of
CONFIRMATION provided by DNSBench.

Here's the top resolver - note the average average milliseconds
peak at 0.024 - nice:

1. 1. 1. 1 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.009 | 0.024 | 0.260 | 0.006 | 0.250 |
- Cached Name | 0.009 | 0.013 | 0.020 | 0.002 | 0.154 |
- Uncached Name | 0.014 | 0.044 | 0.260 | 0.062 | 1.409 |
- DotCom Lookup | 0.015 | 0.017 | 0.024 | 0.002 | 0.118 |
---<-------->---+-------+-------+-------+-------+-------+
one.one.one.one
APNIC AND CLOUDFLARE DNS RESOLVER PROJECT

... and so on.

A fastest test of 0.024 milliseconds compared to my System's fastest
test of 0.035 milliseconds means ... what?

I dunno, yet.

I get to study tons of results like that, and start swapping DNS servers
into my System and see how things feel.

And test again, and again, as well as confirm via all the Internet speed
tests out there.

Busy, busy, busy.

Are we having fun yet?

;-)

- - - - -

So, back to you, across your various DNSBench Benchmark results
in Tabular Data, what's your average average millisecond range from
worst System to best possible tested alternative?

And again, after a few 5x and longer Benchmarks next month?

It's what we do.

Thanks.
Click to expand...
peterblaise, I want to thank-you and everyone who responded to me. In the end the results that were good and consistent were 1.1.1.1 and 1.0.0.1 (Cloudflare) and 129.250.35.251 (NTT America, Inc.). My ASUS RT-AX88U Pro was on Spectrums approved list when I bought it but it isn't anymore. I wonder if this could have a negative effect on my router's performance? I'm sure it does. In the end my router is working better now that I changed my DNS settings. My router also just recently updated it's firmware and it changed the whole look of the menu and the settings. It's almost like getting a used to a new operating system because it looks much different and the choices are different also.
 
Cool - here they are for me at the moment from the Delaware Bay US
via Xfinity Comcast, a 5x Benchmark Speed 20 msec ( defaults ), note
the average average is 0.026 to 0.032 milliseconds for me at the
moment, and the range shows variability of 0.012 to 3.337
milliseconds response time <-- there's your "Every Time I Run
DNS Benchmark I Get Different Conclusions" - the Internet is
variable:

UTC: 2025-12-25, from 14:39:13 to 14:39:36, for 00:23.666

1. 1. 1. 1 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.012 | 0.026 | 0.642 | 0.007 | 0.269 |
- Cached Name | 0.012 | 0.014 | 0.031 | 0.002 | 0.143 |
- Uncached Name | 0.014 | 0.048 | 0.642 | 0.081 | 1.688 |
- DotCom Lookup | 0.014 | 0.016 | 0.028 | 0.002 | 0.125 |
---<-------->---+-------+-------+-------+-------+-------+
one.one.one.one
APNIC AND CLOUDFLARE DNS RESOLVER PROJECT


1. 0. 0. 1 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.012 | 0.027 | 1.010 | 0.007 | 0.259 |
- Cached Name | 0.012 | 0.013 | 0.021 | 0.001 | 0.077 |
- Uncached Name | 0.013 | 0.051 | 1.010 | 0.100 | 1.961 |
- DotCom Lookup | 0.014 | 0.016 | 0.023 | 0.001 | 0.063 |
---<-------->---+-------+-------+-------+-------+-------+
one.one.one.one
APNIC AND CLOUDFLARE DNS RESOLVER PROJECT


129.250. 35.251 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.012 | 0.032 | 3.337 | 0.011 | 0.344 |
- Cached Name | 0.012 | 0.013 | 0.021 | 0.001 | 0.077 |
- Uncached Name | 0.013 | 0.069 | 3.337 | 0.250 | 3.623 |
- DotCom Lookup | 0.013 | 0.014 | 0.024 | 0.001 | 0.071 |
---<-------->---+-------+-------+-------+-------+-------+
y.ns.gin.ntt.net
NTT AMERICA INC.
- - - - -

What are your average average and range?

Thanks.
 
peterblaise said:
Cool - here they are for me at the moment from the Delaware Bay US
via Xfinity Comcast, a 5x Benchmark Speed 20 msec ( defaults ), note
the average average is 0.026 to 0.032 milliseconds for me at the
moment, and the range shows variability of 0.012 to 3.337
milliseconds response time <-- there's your "Every Time I Run
DNS Benchmark I Get Different Conclusions" - the Internet is
variable:

UTC: 2025-12-25, from 14:39:13 to 14:39:36, for 00:23.666

1. 1. 1. 1 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.012 | 0.026 | 0.642 | 0.007 | 0.269 |
- Cached Name | 0.012 | 0.014 | 0.031 | 0.002 | 0.143 |
- Uncached Name | 0.014 | 0.048 | 0.642 | 0.081 | 1.688 |
- DotCom Lookup | 0.014 | 0.016 | 0.028 | 0.002 | 0.125 |
---<-------->---+-------+-------+-------+-------+-------+
one.one.one.one
APNIC AND CLOUDFLARE DNS RESOLVER PROJECT


1. 0. 0. 1 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.012 | 0.027 | 1.010 | 0.007 | 0.259 |
- Cached Name | 0.012 | 0.013 | 0.021 | 0.001 | 0.077 |
- Uncached Name | 0.013 | 0.051 | 1.010 | 0.100 | 1.961 |
- DotCom Lookup | 0.014 | 0.016 | 0.023 | 0.001 | 0.063 |
---<-------->---+-------+-------+-------+-------+-------+
one.one.one.one
APNIC AND CLOUDFLARE DNS RESOLVER PROJECT


129.250. 35.251 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.012 | 0.032 | 3.337 | 0.011 | 0.344 |
- Cached Name | 0.012 | 0.013 | 0.021 | 0.001 | 0.077 |
- Uncached Name | 0.013 | 0.069 | 3.337 | 0.250 | 3.623 |
- DotCom Lookup | 0.013 | 0.014 | 0.024 | 0.001 | 0.071 |
---<-------->---+-------+-------+-------+-------+-------+
y.ns.gin.ntt.net
NTT AMERICA INC.
- - - - -

What are your average average and range?

Thank
Click to expand...
Detailed benchmark statistics, sorted by best DNS resolver
performance, with the "best" average name retrieval speed
listed first, updated and re-sorted during benchmarking:
Code: 
  UTC: 2025-12-25, from 15:10:40 to 15:17:38, for 06:57.444

                    2606:4700:4700::1111
        IPv6      |  Min  |  Avg  |  Max  |Std.Dev| Jitter|
  ----------------+-------+-------+-------+-------+-------+
  - Average Delay | 0.013 | 0.032 | 0.677 | 0.008 | 0.250 |
  - Cached Name   | 0.013 | 0.017 | 0.047 | 0.003 | 0.176 |
  - Uncached Name | 0.013 | 0.058 | 0.677 | 0.091 | 1.569 |
  - DotCom Lookup | 0.015 | 0.020 | 0.063 | 0.004 | 0.200 |
  ---<-------->---+-------+-------+-------+-------+-------+
                       one.one.one.one
          APNIC AND CLOUDFLARE DNS RESOLVER PROJECT


  166.102.165. 11 | The DNS resolver at this IP address is
  not answering queries for all test domains & variations.
  It should not be used for normal client-based resolution.
  ---<-------->---+-------+-------+-------+-------+-------+
                    nsvip01.windstream.net
                WINDSTREAM COMMUNICATIONS LLC


    1.  1.  1.  1 |  Min  |  Avg  |  Max  |Std.Dev| Jitter|
  ----------------+-------+-------+-------+-------+-------+
  - Average Delay | 0.013 | 0.032 | 0.597 | 0.008 | 0.250 |
  - Cached Name   | 0.013 | 0.017 | 0.038 | 0.003 | 0.176 |
  - Uncached Name | 0.015 | 0.058 | 0.597 | 0.080 | 1.379 |
  - DotCom Lookup | 0.016 | 0.022 | 0.053 | 0.004 | 0.182 |
  ---<-------->---+-------+-------+-------+-------+-------+
                       one.one.one.one
          APNIC AND CLOUDFLARE DNS RESOLVER PROJECT


    1.  0.  0.  1 |  Min  |  Avg  |  Max  |Std.Dev| Jitter|
  ----------------+-------+-------+-------+-------+-------+
  - Average Delay | 0.013 | 0.033 | 0.678 | 0.009 | 0.273 |
  - Cached Name   | 0.013 | 0.017 | 0.037 | 0.003 | 0.176 |
  - Uncached Name | 0.013 | 0.059 | 0.678 | 0.086 | 1.458 |
  - DotCom Lookup | 0.017 | 0.022 | 0.090 | 0.005 | 0.227 |
  ---<-------->---+-------+-------+-------+-------+-------+
                       one.one.one.one
          APNIC AND CLOUDFLARE DNS RESOLVER PROJECT


                    2606:4700:4700::1001
        IPv6      |  Min  |  Avg  |  Max  |Std.Dev| Jitter|
  ----------------+-------+-------+-------+-------+-------+
  - Average Delay | 0.013 | 0.033 | 0.655 | 0.008 | 0.242 |
  - Cached Name   | 0.013 | 0.018 | 0.032 | 0.003 | 0.167 |
  - Uncached Name | 0.015 | 0.059 | 0.655 | 0.090 | 1.525 |
  - DotCom Lookup | 0.016 | 0.022 | 0.093 | 0.009 | 0.409 |
  ---<-------->---+-------+-------+-------+-------+-------+
                       one.one.one.one
          APNIC AND CLOUDFLARE DNS RESOLVER PROJECT


                      2620:119:53::53
        IPv6      |  Min  |  Avg  |  Max  |Std.Dev| Jitter|
  ----------------+-------+-------+-------+-------+-------+
  - Average Delay | 0.009 | 0.037 | 0.537 | 0.012 | 0.324 |
  - Cached Name   | 0.009 | 0.018 | 0.155 | 0.009 | 0.500 |
  - Uncached Name | 0.013 | 0.063 | 0.537 | 0.078 | 1.238 |
  - DotCom Lookup | 0.013 | 0.030 | 0.084 | 0.017 | 0.567 |
  ---<-------->---+-------+-------+-------+-------+-------+
                       dns.opendns.com
                      CISCO-UMBRELLA, US

Right now I'm using DNS Server: 1.1.1.1 and 129.250.35.251
 
Note, highlight any text and use the GRC Forum top controls to change
to Courier or Code for monospaced fonts:

The range shared is:

2606:4700:4700::1111
IPv6 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.013 | 0.032 | 0.677 | 0.008 | 0.250 |
- Cached Name | 0.013 | 0.017 | 0.047 | 0.003 | 0.176 |
- Uncached Name | 0.013 | 0.058 | 0.677 | 0.091 | 1.569 |
- DotCom Lookup | 0.015 | 0.020 | 0.063 | 0.004 | 0.200 |
---<-------->---+-------+-------+-------+-------+-------+
one.one.one.one
APNIC AND CLOUDFLARE DNS RESOLVER PROJECT

. . .

2620:119:53::53
IPv6 | Min | Avg | Max |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.009 | 0.037 | 0.537 | 0.012 | 0.324 |
- Cached Name | 0.009 | 0.018 | 0.155 | 0.009 | 0.500 |
- Uncached Name | 0.013 | 0.063 | 0.537 | 0.078 | 1.238 |
- DotCom Lookup | 0.013 | 0.030 | 0.084 | 0.017 | 0.567 |
---<-------->---+-------+-------+-------+-------+-------+
dns.opendns.com
CISCO-UMBRELLA, US

That's:

average average range 0.032 to 0.037 milliseconds​
​
fastest to slowest range 0.009 to 0.677 milliseconds​

And, apparently, it 'feels' great so far.

I notice:

the fastest DNS server has the slowest max​
​
the slowest DNS server has the fastest min​

Hence, our observations:

"Every Time I Run DNS Benchmark I Get Different Conclusions."​
​
"The Internet is variable."​

I see that.

Clearly.

Thanks.
 
peterblaise said:
Note, highlight any text and use the GRC Forum top controls to change
to Courier or Code for monospaced fonts:
Click to expand...
If you use a code block, it looks even better ;)
1766687059518.png

Code: 
2606:4700:4700::1111
           IPv6 | Min   | Avg   | Max   |Std.Dev| Jitter|
----------------+-------+-------+-------+-------+-------+
- Average Delay | 0.013 | 0.032 | 0.677 | 0.008 | 0.250 |
- Cached Name   | 0.013 | 0.017 | 0.047 | 0.003 | 0.176 |
- Uncached Name | 0.013 | 0.058 | 0.677 | 0.091 | 1.569 |
- DotCom Lookup | 0.015 | 0.020 | 0.063 | 0.004 | 0.200 |
---<-------->---+-------+-------+-------+-------+-------+
one.one.one.one
APNIC AND CLOUDFLARE DNS RESOLVER PROJECT
 
You must log in or register to reply here.

Similar threads

S
CGNAT & Running DNS Benchmark
Replies
5
Views
997
DNS Benchmark
SCFan
S
Teddy7
  • Contains 1 staff post(s)
DNS Benchmark - A winner!
Replies
1
Views
314
DNS Benchmark
Steve
Steve
M
  • Contains 1 staff post(s)
DNS Benchmark 2.0 confusion
Replies
5
Views
673
DNS Benchmark
peterblaise
peterblaise
I
  • Contains 10 staff post(s)
DNS Benchmark V2 - Lost connectivity
Replies
54
Views
3K
DNS Benchmark
peterblaise
peterblaise
T
  • Contains 3 staff post(s)
DNS Benchmark v2 Blocked by Windows
Replies
13
Views
944
DNS Benchmark
Steve
Steve
Top Bottom
Back