Should you be worried about 1, 5, or 10 ms of input lag? Use Latency Split Test (LST) and find out!

[jorimt]

if I do decid to cap it do I turn of reflex? Or leave it on with the fps cap?

Reflex is the automatic version of a manually set cap, so you don't need both. I.E. only use a manual cap to prevent max GPU usage if Reflex isn't available.

[mago]

TV OLED
really hard to notice the diff, can be the hz can be the stutters

Viper 8k @ 1600DPI / 8Khz
1440p @ 120HZ

mb adding random input lag with stddev like in games would be same what beneficial

[MatrixQW]

I never mentioned that to get steady 1000 fps, excluding core 0 and all HT/SMT cores, is necessary.
I have an I7-4790K. Don't know how affinity will be with Intel CPUs with P and E cores.
This happens because core 0 gets a very high load and GPU interrupts (ISR/DPC) cause the drop in performance.

Try this CPU Affinity Mask Calculator. In the shortcut properties I used affinity:
- Start in: "D:\Apps\Latency Split Test\WindowsNoEditor\LatencySplitTest\Binaries\Win64"
- Target: %ComSpec% /C start "" /affinity 54 "LatencySplitTest-Win64-Shipping.exe"

Probably no one cares about this test anymore, but if someone wants to try, the affinity should help.

[Espionage724]

Gamers want the lowest latency possible, but how much does this actually matter? Can you even feel the difference between 5 or 10 or 20 milliseconds of lag? Aperture Grille's Latency Split Test (LST) is a program designed to help you determine your personal sensitivity to lag.

Human perception can vary; I want my computer having as little-to-no latency as possible consistently

Interesting test though

[RealNC]

Btw, the most important latency test is mouse look (meaning when the camera/viewport in a game is directly tied to mouse movement.)

IMO, any testing tool that doesn't test that explicitly is not that useful. Latency on mouse clicks is not as important. Mouse look is. Mouse clicks (or gamepad button presses) feel about the same to me at 20ms and 40ms. But mouse look? Even a 10ms increase is immediately noticeable to me, as I can feel the camera being slightly behind my hand movement.

[nickchraj]

Here are my results, pretty sure i can do better if i focus enough. also this is on 60hz

[mago]

mb with 700hz, people / pro players can do 0.75ms
will prove that every ms count

[netborg]

This test is pretty bad and in no way can represent what humans latency perception threshold is.

The reason is pretty simple: It only updates a tiny fraction of what you're seeing, you're burning ~100 lines onto the retina (sample and hold blur) and now you expect that adding one line every frame is somehow related to a real game which updates the whole screen every frame. That's clearly not working out.