google.com or duende.link/06oct26: which redirect is faster?
Measured from Washington, D.C. on October 16, 2026. Test it again, or try your own URL.
Result · Washington, D.C. · median of 10 runs
duende.link/06oct26 answered in 15 ms. google.com took 26 ms.
| google.comA | duende.link/06oct26B | |
|---|---|---|
| Median first byte | 26 ms | 15 ms |
| p90 | 27 ms | 16 ms |
| DNS · connect · TLS · wait | 2 · 2 · 6 · 16 ms | 2 · 2 · 8 · 3 ms |
| Status | 301 Moved Permanently | 301 Moved Permanently |
| Lands on | https://www.google.com/ | https://duendesoftware.com/blog/bridge-azure-workload-identity-to-client-identity-with-dynamic-client-registration?utm_campaign=content&utm_medium=social&utm_source=social |
| Served by | Google server: gws | RedirHub x-powered-by: RedirHub |
| Hops to final page | 1 | 1 |
| Certificate | Valid | Valid |
| Rank, last 7 days | Faster than 53% | Faster than 70% |
Reproduce it
Run the same test yourself
Copy this into a terminal on macOS or Linux. It already holds both URLs, so paste it and press Enter. Only curl is needed.
Your numbers will differ from ours: they depend on where you run it and your network.
for u in 'https://google.com/' 'https://duende.link/06oct26'; do
for i in $(seq 10); do
curl -s -o /dev/null --max-redirs 0 --max-time 10 \
-w '%{time_namelookup} %{time_connect} %{time_appconnect} %{time_starttransfer} %{http_code}\n' "$u"
done | sort -n -k4 | awk -v u="$u" '{r[NR]=$0} END{split(r[int((NR+1)/2)],m," ");
printf "%-28s %s DNS %4.0f connect %4.0f TLS %4.0f first byte %4.0f ms\n", u, m[5], m[1]*1000, (m[2]-m[1])*1000, (m[3]>0?m[3]-m[2]:0)*1000, m[4]*1000}'
doneThe benchmark
How “faster than X%” is worked out
The number comes from the redirects people test on this page, plus a fixed list of well-known redirects measured every day, so each location always has a baseline.
Every test is kept for 7 days
Each URL tested here stores its median first-byte time and test location. One entry per URL, so testing the same link ten times doesn't tilt the result.
Compared from the same place
Your result is ranked against URLs tested from the same location, so a test from Tokyo is never compared with one from Washington, D.C.
Your rank is a percentile
“Faster than 82%” means 82% of the URLs tested in the last 7 days took longer than yours.
By provider
How fast is each redirect provider?
Median first byte from Washington, D.C. over the last 7 days, for every provider with at least one tested URL. Open one for its locations, rank and where its time goes.
- Fastly redirect speed5 URLs11 ms
- Amazon CloudFront redirect speed1 URL11 ms
- Short.io redirect speed2 URLs14 ms
- RedirHub redirect speed5 URLs15 ms
- Microsoft Azure redirect speed1 URL15 ms
- Bitly redirect speed3 URLs25 ms
- Amazon redirect speed1 URL25 ms
- Meta redirect speed1 URL25 ms
- Google redirect speed1 URL26 ms
- Envoy redirect speed3 URLs29 ms
- Rebrandly redirect speed1 URL32 ms
- Vercel redirect speed1 URL32 ms
- Cloudflare redirect speed3 URLs39 ms
- Buffer redirect speed1 URL40 ms
- Akamai redirect speed3 URLs41 ms
- Dub redirect speed1 URL41 ms
- LinkedIn redirect speed1 URL62 ms
- TinyURL redirect speed2 URLs69 ms
- YouTube redirect speed1 URL79 ms
- redirect.pizza redirect speed2 URLs161 ms
- Spotify redirect speed1 URL184 ms
- Cuttly redirect speed1 URL190 ms
- urllo redirect speed3 URLs194 ms
- BL.INK redirect speed2 URLs239 ms
- nginx redirect speed4 URLs341 ms
Method
What the test measures
DNS
Looking up the redirect's domain.
Connect
Opening a TCP connection to the closest server.
TLS
The HTTPS handshake and certificate check.
Server wait
Until the 301 and its Location header arrive.
Only the redirect response is timed, not the destination page, so a slow destination does not count against the redirect. Hops are counted separately. The tool runs on Vercel Functions in Washington, D.C., Frankfurt and Tokyo, not on our redirect network, and alternates A and B on every run.
FAQ