DNS Benchmark, Which DNS Server is best for me ?

[tjp1980]

DNS Benchmark, Which DNS Server is best for me ?

Good day,
I first want to thank Steve for his work on this DNS Benchmark program.
I'm not sure if this is where I ask this question. I apologize if it's not the right place.

I ran the DNS Benchmark program two times today (8-24-2025). Once at midnight and the other time at 3:45pm.

I watched the following You tube video to help try to understand how to use this program.
DNS Demystified: Everything You Should Know for Faster Internet!

I also read some information on how to use the program from www.grc.com. I also read some of the DNS Benchmark Introduction and Conclusions of each test.

I'm still having trouble understanding.
I see a newer version of the DSN Benchmark program is coming out soon and my understanding is it will automatically tell you which is the best DNS for you.
But until then please help.

Here is a screenshot of the results of first DNS Benchmark test today at 12:00am midnight. This test was done by our desktop computer connected to the internet by Wi-Fi. The router is in the next room away. But I forgot to turn off our Ring camera, and Ring Chime device that was connected to our internet. So, not all devices were off. But I made sure all phones were not connected to the internet at the time of this test.

Here is a screenshot of the results of the second DNS Benchmark test today at 3:45pm.
This test was done by our desktop computer connected to the internet by Wi-Fi. The router is in the next room away. I made sure that all other devices were not connected to our internet at this time.

I forgot to copy the Tabular Data for the test that was done at midnight. But I have the Tabular Data from the test at 3:45pm. Not sure if you need this data or if the picture graphs are all you need to help decide what would be our best DNS.

We have Xfinity / Comcast for our Cable internet provider.

Which DNS Server is best for me ?

Thank you very much in advance.

 

[peterblaise]

DNSBench v1 and upcoming DNSBench v2 BOTH suggest FASTER
public DNS Nameserver resolvers, if available and reliable.

DNSBench v1 is ONLY IPv4.

DNSBench v2 will add IPv6 for hardware DNS Nameserver
resolvers, and DoH and DoT for browser DNS Nameserver resolvers.

DNSBench v1 [ Conclusions ] tab says what for you today?.

 

[tjp1980]

I just noticed that after uploading the screenshots the quality has reduced a lot.

I'll give links below to the images in a google cloud drive to be able to see the full quality.

Here is a screenshot of the results of first DNS Benchmark test today at 12:00am midnight. This test was done by our desktop computer connected to the internet by Wi-Fi. The router is in the next room away. But I forgot to turn off our Ring camera, and Ring Chime device that was connected to our internet. So, not all devices were off. But I made sure all phones were not connected to the internet at the time of this test.
Screenshot 2025-08-24, 12am

Here is a screenshot of the results of the second DNS Benchmark test today at 3:45pm.
This test was done by our desktop computer connected to the internet by Wi-Fi. The router is in the next room away. I made sure that all other devices were not connected to our internet at this time.
Screenshot 2025-08-24, 345pm

Hope this helps to see the images better.
Thank you very much in advance again for any help.

 

[tjp1980]

DNSBench v1 and upcoming DNSBench v2 BOTH suggest FASTER
public DNS Nameserver resolvers, if available and reliable.

DNSBench v1 is ONLY IPv4.

DNSBench v2 will add IPv6 for hardware DNS Nameserver
resolvers, and DoH and DoT for browser DNS Nameserver resolvers.

DNSBench v1 [ Conclusions ] tab says what for you today?.

DNSBench v1 [ Conclusions ] tab says what for you today?.

Good day,
Thank you for responding.

The Conclusions and Tabular Data for the test today at 12am with two ring devices still connected to our internet is as follows in this attached text document file cause it's too long to copy paste here.
=================================

The Conclusions for the test today at 3:45pm with no other devices connected to our internet except for our desktop we performed the test from connected to our internet is as follows in the attached text document file. Also I forgot to copy the Tabular Data for this test result.
=================================

I hope I listed everything right.
I am able to do another DNS Benchmark test again right now and copy all the results here if needed.
It's 8-24-2025, at 7:20pm here.

Thank you very much in advance for any help.

 

[peterblaise]

Here's an example of mine, Cox Cable, Washington DC US area,
compared to GRC-discovered Default Public DNSSec DNS
Nameserver Resolvers:

The [ Tabular Data ] tab reads, from the fastest Public resolver at the
top on down to my first Cox-provided resolver:

Final benchmark results, sorted by nameserver performance:
(average cached name retrieval speed, fastest to slowest)

198.153.192. 1 | Min | Avg | Max |Std.Dev|Reliab%|
----------------+-------+-------+-------+-------+-------+
- Cached Name | 0.007 | 0.009 | 0.012 | 0.001 | 100.0 |
- Uncached Name | 0.009 | 0.046 | 0.232 | 0.058 | 100.0 |
- DotCom Lookup | 0.010 | 0.036 | 0.070 | 0.023 | 100.0 |
---<-------->---+-------+-------+-------+-------+-------+
··· no official Internet DNS name ···
SECURITYSERVICES, US


156.154. 71. 25 | Min | Avg | Max |Std.Dev|Reliab%|
----------------+-------+-------+-------+-------+-------+
- Cached Name | 0.007 | 0.009 | 0.013 | 0.001 | 100.0 |
- Uncached Name | 0.008 | 0.047 | 0.215 | 0.058 | 100.0 |
- DotCom Lookup | 0.009 | 0.035 | 0.069 | 0.022 | 100.0 |
---<-------->---+-------+-------+-------+-------+-------+
··· no official Internet DNS name ···
SECURITYSERVICES, US


9. 9. 9. 9 | Min | Avg | Max |Std.Dev|Reliab%|
----------------+-------+-------+-------+-------+-------+
- Cached Name | 0.007 | 0.010 | 0.013 | 0.001 | 100.0 |
- Uncached Name | 0.009 | 0.042 | 0.239 | 0.056 | 100.0 |
- DotCom Lookup | 0.015 | 0.022 | 0.042 | 0.009 | 100.0 |
---<-------->---+-------+-------+-------+-------+-------+
dns9.quad9.net
QUAD9-AS-1, US


208. 67.222.123 | Min | Avg | Max |Std.Dev|Reliab%|
----------------+-------+-------+-------+-------+-------+
- Cached Name | 0.007 | 0.010 | 0.014 | 0.001 | 100.0 |
- Uncached Name | 0.009 | 0.044 | 0.170 | 0.040 | 100.0 |
- DotCom Lookup | 0.011 | 0.028 | 0.074 | 0.021 | 100.0 |
---<-------->---+-------+-------+-------+-------+-------+
familyshield.sse.cisco.com
CISCO-UMBRELLA, US


68.105. 29. 11 | Min | Avg | Max |Std.Dev|Reliab%|
----------------+-------+-------+-------+-------+-------+
+ Cached Name | 0.007 | 0.010 | 0.015 | 0.002 | 100.0 |
+ Uncached Name | 0.010 | 0.046 | 0.222 | 0.053 | 100.0 |
+ DotCom Lookup | 0.008 | 0.026 | 0.081 | 0.017 | 100.0 |
---<-------->---+-------+-------+-------+-------+-------+
cdns6.cox.net
ASN-CXA-ALL-CCI-22773-RDC, US

And my [ Conclusions ] tab says:

System nameservers are SLOWER than 2 public alternatives!​

This benchmark found 2 publicly available DNS nameservers that ​

are reliably 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.​

​

Recommended Actions:​

​

With at least 95% certainty: Based upon a statistical analysis of the ​

spread in timing value samples received during the benchmark, ​

there is at least a 95% certainty that the performance conclusions ​

stated above are correct. But even so, since changing DNS ​

nameservers requires thought and effort, it's something you want to ​

be sure about. Therefore, since these results represent a single ​

snapshot in time, you may wish to confirm that the faster alternative ​

nameservers are consistently faster than your system's currently ​

configured nameservers, and that those public alternatives don't ​

have any negative characteristics such as being colored orange to ​

signify that they redirect mistaken URLs to an advertising-laden ​

search page rather than returning an error (which will be a concern ​

to some users).​

​

You may also wish to check the relative performance at different ​

times of day to make sure that the performance improvement over ​

your system's current nameservers is reliable throughout the day.​

​

And you may wish to make sure that the alternative nameservers ​

are enough faster than what you are currently using for the ​

improvement to be worth changing away from what you're currently ​

using. (This test is only saying that it's 95% sure they are any ​

amount faster.)​

TOGETHER means that, though there's a difference in responsiveness,
milliseconds to 'resolve' a DNS lookup:

Fastest: My Cox <-- default:​

Average ms Average ms​

0.009 0.010​

0.046 0.046​

0.036 0.026​

... the differences may not be significant or consistent throughout the
day and week,

So, test, test, and test again.

- - - - -

Sometimes, 'all we get' from DNSBench is confirmation that we are
getting what we pay our IPS for - mine are apparently already
top-notch, fast, and reliable.

Your graphs aren't measured or interpreted, so check the [ Tabular
Data ] tab and [ Conclusion ] tab for more information, as above.

And tell us more.

Thanks.

 

[peterblaise]

Ah, cross-posting.

Shared data says, for example, across 2 tests:

System nameservers are SLOWER than 14 public alternatives!​

System nameservers are SLOWER than 3 public alternatives!​

​

Security Services: Google <-- default:​

Average ms Average ms​

0.057 0.080​

0.084 0.114​

0.083 0.088​

If you swap to Security Services resolvers, do you 'feel' an
improvement in Internet responsiveness compared to Google
resolvers?

I'm curious how both of these Public resolver offerings compare to
your ISP-provided DNS Nameserver resolvers.

In other words, why did you switch to Google, and what did you
switch from?

There are many reasons to select DNS Nameserver resolvers, and
speed and reliability, though testable, are only two.

There's also security, anonymity, and filtering stuff, and probably
many other differences between DNS Nameserver resolver offerings.

So, is there more to what you are troubleshooting or trying to
confirm?

Thanks.

 

[DanR]

Which DNS Server is best for me ?

Faster is better. The results are ranked with the fastest at the top and the slowest at the bottom in the Response Time tab..

Your two current system resolvers, with the black border around them, are not the fastest available.

Any of the 154.154.70.x resolvers at the top of the list would appear to be good choices for you.

Add one or two of them to your system resolvers and then rerun DNSB.

The Conclusions tab should now be a little less ambiguous.

 

[peterblaise]

Comcast 75.75.75.75 seems fastest, right?

 

[tjp1980]

Ah, cross-posting.

Shared data says, for example, across 2 tests:

System nameservers are SLOWER than 14 public alternatives!​

System nameservers are SLOWER than 3 public alternatives!​

​

Security Services: Google <-- default:​

Average ms Average ms​

0.057 0.080​

0.084 0.114​

0.083 0.088​

If you swap to Security Services resolvers, do you 'feel' an
improvement in Internet responsiveness compared to Google
resolvers?

I'm curious how both of these Public resolver offerings compare to
your ISP-provided DNS Nameserver resolvers.

In other words, why did you switch to Google, and what did you
switch from?

There are many reasons to select DNS Nameserver resolvers, and
speed and reliability, though testable, are only two.

There's also security, anonymity, and filtering stuff, and probably
many other differences between DNS Nameserver resolver offerings.

So, is there more to what you are troubleshooting or trying to
confirm?

Thanks.

I switched our Comcast DSN to Google's DNS to see if speed is faster. Read and watched videos saying google can be faster and also Cloudflare DNS. Of course it depends on your location etc.

If you swap to Security Services resolvers, do you 'feel' an
improvement in Internet responsiveness compared to Google
resolvers?

Which Security Services specifically?
These are all the Security Services listed in order as it was on the Tabular Data.
Should I try the top three?

156.154. 70. 25

156.154. 70. 22

156.154. 70. 1

198.153.194. 1

156.154. 71. 22

156.154. 71. 1

156.154. 71. 25

198.153.192. 1

Thank you again in advance for your help.

 

[peterblaise]

After seeing the other test, Comcast seems faster.

Knowing that the ISP is Comcast, that makes sense.

What kind of router - Comcast?

- - - - -

Speed-wise, there are a gazillion browser-based websites that report
all sorts of Internet performance stuff; here are a few.

https://speed.cloudflare.com/​

​

http://speedof.me/​

​

https://www.google.com/search?q=internet+speed+test​

comes up inside a search result, no link​

​

https://fiber.google.com/speedtest/​

What do you 'feel;' when using any DNS Nameserver resolver?

Any difference in the feeling of responsiveness with one or another?

 

[tjp1980]

After seeing the other test, Comcast seems faster.

Knowing that the ISP is Comcast, that makes sense.

What kind of router - Comcast?

- - - - -

Speed-wise, there are a gazillion browser-based websites that report
all sorts of Internet performance stuff; here are a few.

https://speed.cloudflare.com/​

​

http://speedof.me/​

​

https://www.google.com/search?q=internet+speed+test​

comes up inside a search result, no link​

​

https://fiber.google.com/speedtest/​

What do you 'feel;' when using any DNS Nameserver resolver?

Any difference in the feeling of responsiveness with one or another?

I have the Arris SBG8300 Surfboard cable Modem/Router combo. It's a all in one unit.
I put it into bridge mode so this turns off the router but now functions only as a modem.
I have a TP-Link Deco X55 AX3000 Wi-Fi 6 Mesh System. It comes with three Deco units. With one of them directly connected to the Arris modem functions as a router. The other two Deco's function as nodes/clients. But all of them can function as a router. But only one can function as a router in a setup with other Deco's.

We pay for 400mb. We get about 470mb download on our desktop computer.
We have Xfinity/Comcast cable internet.

Yes, depending on what speed test service you use depends on what speed tests results it gives you.

we usually use:

https://speedtest.xfinity.com/

Speedtest by Ookla - The Global Broadband Speed Test

Use Speedtest on all your devices with our free desktop and mobile apps.

www.speedtest.net

I switched our DNS back to Xfinity/Comcast for now.
Maybe tomorrow I will try other DNS.
Thank you very much for your help.

 

[PHolder]

In most cases, your ISP's DNS supplied to your modem/router automatically by DHCP is going to be the fastest for most users, simply because it's closest (it's on the network you, the customer, are on.) There are only a couple of reasons to ever change them, IMHO. One is if you want the features some other DNS offers (there are security featured ones like Quad9, and paid features ones like NextDNS.) The other is if the ISP has really neglected/overloaded their DNS servers and they're under-performing.

 

[peterblaise]

For our archives today, and any day anyone visits these forums, let's
ask our collective brain:

Q: Google, What are important reasons to manually select other than the default ISP DNS Nameserver resolvers?

A: [ edited to headlines ]
Security,
Protection from malware and phishing,
Defense against DNS attacks.
Encrypted DNS queries,
Limit ISP tracking,
Improve performance,
Improve reliability,
Content control and filtering,
Parental controls,
Ad and tracker blocking,
Customizable filtering,
Circumvent censorship,
Bypass DNS blocking,
Evade DNS tampering ...

Thanks.