CPU Benchmark Test
This CPU benchmark test measures how fast your processor really is — single-core speed, multi-core speed and how well the cores scale — in about 6 seconds, right in your browser. No download, no sign-up, no admin rights, nothing uploaded. One honest limit up front: a browser score only compares within the same browser, so this page reports the raw numbers and what they mean, not a made-up tier.
The line below shows what your browser says about this device: how many logical cores it reports, how much memory, and whether Web Workers are available. The benchmark needs Workers for the multi-core phase — if they are blocked, the page says so and runs what it can on the main thread instead.
Reading this browser…
1 · Run the benchmark — about 6 seconds
Press Start and the test runs the same fixed workload twice: first on one core for 3 seconds, then on every logical core at once for 3 seconds. The workload is integer math, sorting, a memory walk and floating-point multiply-adds — chosen because it barely depends on which browser you use. Every run is checksum-checked, so a broken run is never scored. Close other tabs first, and keep this tab in front for the whole run.
Not run yet — single-core 3 s, then multi-core 3 s.
Single-core
—
Multi-core
—
Scaling
—
Threads used
—
2 · What the workload is made of
The single-core phase breaks the workload into four parts, so a memory-bound machine reads differently from a compute-bound one. Each rate is work units per second on one core — the same units as the headline scores, so the four parts add up to the story of the whole run.
Integer math
—
Sorting
—
Memory walk
—
Floating point
—
3 · Stress test — 60 seconds, all cores
Press Start and every core runs at 100% for 60 seconds. The test compares the rate in the first 10 seconds with the rate in the last 10 seconds: a machine that holds its pace is cooling well, one that fades is throttling. Stop any time — closing the tab stops the load immediately, and the page never reads your temperature, because no web page can.
Not run yet — 60 seconds at full load.
First 10 s rate
—
Last 10 s rate
—
Drop
—
4 · Runs this session
Every run you do on this page is kept here, so you can see the pattern instead of trusting one number. Run the benchmark three times: the first run is often the lowest, and a score that falls on every run points to cooling, while one that is low every time points to a setting.
| Run | Single-core | Multi-core | Scaling | Threads |
|---|---|---|---|---|
| No runs yet — press “Start benchmark” above. | ||||
5 · Your CPU report
The report reads the latest run, the scaling factor and the run history, and says in plain words what the numbers mean — whether the cores scale well, whether the machine looks like it is throttling, and what to check first. Copy the text version to paste into a support ticket, a sale listing or a message to a friend.
Go deeper with a dedicated test:
FPS Test · Refresh Rate Test · Ghosting Test · Dead Pixel Test · Keyboard Test · Mouse Test · Gamepad Test · Touch Screen Test
Honest limits
A web page only sees the work the browser lets it do. It cannot read your CPU temperature, clock speed, fan speed or processor model — no browser API exposes those on any platform — so this page never claims to know them. It counts logical threads, not physical cores, and the browser is not always honest about those either: Safari clamps the figure, private and anti-fingerprinting modes clamp it further, and a hybrid chip counts its performance and efficiency cores in the same total. The score measures how fast this browser's JavaScript engine runs this workload on this machine, so Chrome, Edge, Firefox and Safari give different numbers on the same computer. Compare only scores taken in the same browser, and read a run against your own other runs, never against another machine's number.
How to benchmark your CPU in 3 steps
1 · Set the machine up. Plug the laptop in — many laptops run slower unplugged, even without battery saver — and set the power mode to Best performance (Windows) or turn off Low Power Mode (Mac). Close heavy apps and other browser tabs, and wait a minute after start-up for background tasks to settle. A benchmark measures whatever the machine is doing right now, so a cloud sync or an antivirus scan running beside it becomes part of your score.
2 · Run it three times. Press “Start benchmark” and leave the page alone for about 6 seconds: three seconds on one core, then three seconds on every core. Then press it again twice more. Each run is added to the runs table below the tool, so you can compare them. Use the best or the typical result, not the first one — the first run is often about 10% lower while the browser warms up.
3 · Read the three numbers, not one. The single-core score is how fast one core runs. The multi-core score is the total across all cores working at once. The scaling factor is the multi-core score divided by the single-core score — it is almost always lower than the core count, and that is normal: hyper-threads share a physical core, efficiency cores are slower than performance cores, caches are shared, and processors run at lower clock speeds when every core is busy. A laptop with 16 logical cores might scale by well under 16.
Single-core vs multi-core — why both matter
The single-core score is how fast one core runs. It drives how responsive a computer feels: opening apps, browsing, spreadsheets and most games lean heavily on one or a few fast cores. The multi-core score is the total across all cores working at once. It matters for work that splits into parallel pieces, such as video export, compiling code, 3D rendering and compressing files. A machine with a high single-core score and a modest multi-core score feels quick for everyday use. A low single-core score with many cores can feel slow day to day, even if it renders video well. Here is a worked example. A machine scores 1,200 units per second on one core and 8,400 units per second on 8 threads: the scaling factor is 8,400 ÷ 1,200, which is exactly 7.0× — and 7.0 out of 8 threads is 87.5% efficiency, which scales well. The same machine on battery might score 1,200 single-core and only 4,800 multi-core: scaling 4.0× on 8 threads is 50% efficiency, which points at a power limit, not a slow chip.
What affects the score
Thermal throttling: scores drop on every run. Let it cool — on an older laptop, dust in the fans or dried-out thermal paste is the usual cause. Power mode: every run is low. Windows: Balanced or Best performance. Mac: turn off Low Power Mode. Running on battery: lower than when plugged in. Plug in — many laptops run slower unplugged, even without battery saver. Background apps: scores jump around. Close updates, antivirus scans, sync tools and other tabs. The browser: different numbers on the same PC. Compare only in the same browser, ideally the same version. When a processor gets hot, it slows down to protect itself, so a score that falls on every run points to cooling, while one that is low every time points to a setting.
How to compare two computers fairly
Use the same browser on both, ideally the same version. Plug both in and set the same power mode. Close everything else, and wait a minute after start-up for background tasks to settle. Run the benchmark three times on each and compare typical results, not a single run. Note the logical-cores count, and check the processor name in your system settings so you know what you are comparing. Expect some spread between runs — differences of a few percent are noise. A big gap between two machines with the same processor usually means one is throttling, set to a power-saving mode, or busy in the background.
Benchmarking a used PC before you buy
On a second-hand laptop or desktop, benchmarks show whether the machine performs like its spec says and whether it is overheating. Open your system settings and check the processor, memory and operating system match the listing. Run the benchmark three times in a row — scores that fall noticeably each run point to throttling, which often means a cooling problem. Then run the 60-second stress test and watch whether the rate holds steady: a machine whose rate falls by more than 15% from the first 10 seconds to the last 10 is throttling under sustained load. Finish with the display and input tests on this site — a fast processor in a machine with a dead screen corner or a failing keyboard is still a bad buy.
What this test cannot see
A web page only sees what the browser passes on. It cannot see your CPU temperature, clock speed, fan speed or processor model, and it cannot tell a digitizer fault from a software fault — that is not its job, and it does not pretend otherwise. It cannot measure disk speed either: browsers have no access to raw disk performance. It cannot predict real gaming performance, which depends on the game engine, the drivers and the graphics card as much as on the processor. And a 6-second benchmark will not reveal thermal throttling that only appears after 5 to 10 minutes of load — that is what the 60-second stress test is for, and even that is a quick check, not a replacement for a 30-minute native run. What it can do, honestly, is tell you how fast this browser runs this workload on this machine right now, and whether that speed holds up when you run it again.
Frequently asked questions
How accurate is a browser CPU benchmark?
Accurate enough to compare runs on the same machine in the same browser — and that is the honest limit. The workload on this page (integer math, sorting, a memory walk and floating-point multiply-adds) was chosen because it barely depends on the browser: the same machine in Chrome, Firefox and Safari lands within about 17% on it. But a browser score is not a Geekbench or Cinebench score — the browser adds its own overhead, and different browsers give different numbers on the same machine. Use it to answer “is this PC fast or slow, and is it throttling?” — not to publish a review-grade number.
What does single-core vs multi-core mean?
Single-core measures how fast one core runs the workload — it decides how the computer feels day to day: opening apps, browsing, spreadsheets, and most games, which still lean heavily on one main thread. Multi-core runs the same workload on every logical core at once — it matters for work that splits into parallel pieces, such as video export, compiling code, 3D rendering and compressing files. A machine can be great at one and average at the other, which is why this page reports both numbers and the scaling factor between them instead of hiding them in one combined score.
Which number should I care about — single-core or multi-core?
Whichever matches what you do with the machine. If you mostly browse, work in documents and play games, the single-core score is the one that decides how fast everything feels. If you export video, compile code, render 3D scenes or run batch jobs, the multi-core score is the one that decides how long you wait. The scaling factor tells you how well the extra cores actually help: a high single-core score with a modest multi-core score feels quick for everyday use, while a low single-core score with many cores can feel slow day to day even if it renders video well.
Will the benchmark or the stress test damage my CPU?
No. Modern CPUs have thermal protection built into the hardware: a chip that gets too hot clocks itself down, and if that is not enough the machine switches itself off. A browser benchmark cannot bypass those safeguards — it runs inside the browser's sandbox, and closing the tab stops the load immediately. Expect heat and fan noise during the stress test, and faster battery drain on a laptop. If you would rather not have those, press Stop — the load ends the moment you do.
Why is my score different each time I run it?
Usually by a few percent: the test repeats for three seconds per phase and keeps the work it gets through, and a busy machine gives a slightly different number every time. Bigger swings come from other programs working in the background, a hot device, or a battery-saving mode — close what you can and run it again. The run-history table on this page keeps every run this session so you can see the pattern: the first run is often the lowest, and a score that falls on every run points to cooling, while one that is low every time points to a setting.
How do I test for thermal throttling?
Run the benchmark three times in a row and watch the run-history table. If each run scores noticeably lower than the one before — more than about 15% from the first run to the third — your CPU is thermal throttling as the heatsink saturates: it slows itself down to stay cool. The stress test shows the same thing in one run: it compares the rate in the first 10 seconds with the rate in the last 10 seconds. Clean dust from the laptop exhaust vents, do not run a laptop on a soft bed or blanket that blocks the bottom air intakes, and let the machine cool between runs before you conclude anything.
Can I compare my score with another computer?
Only if you run the test the same way on both. Use the same browser, ideally the same version, on both machines. Plug both laptops in and set the same power mode. Close everything else, and wait a minute after start-up for background tasks to settle. Run the benchmark three times on each and compare the typical result, not a single run — and note the logical-cores count, so you know what you are comparing. Differences of a few percent are noise. A big gap between two machines with the same processor usually means one is throttling, set to a power-saving mode, or busy in the background.
Does the test work on a phone or tablet?
Yes — the benchmark runs on any device with a modern browser: Windows, macOS, Linux, ChromeOS, Android and iOS, with nothing to install. On a phone it takes slightly longer and may show lower scores, because phone chips throttle sooner and the run competes with the rest of the phone. Plug the phone in if you are testing on battery, and keep the tab in front for the whole run — browsers throttle background tabs, and the readings stop meaning anything. One honest limit: this page cannot show your CPU temperature, clock speed, fan speed or processor model — no web page can — so pair it with a local monitor if you need those numbers.
How this test works: every number is measured in your browser from JavaScript running in Web Workers — a same-origin worker file (worker.js next to this page, because the site's Content-Security-Policy allows same-origin scripts but not blob: workers), with a fixed workload of integer math, sorting, a memory walk and floating-point multiply-adds. Every run is checksum-checked before it is scored. No downloads, no sign-up and nothing uploaded.
Related tests
FPS Test
Live frame-rate meter — how many frames your screen really draws.
HzRefresh Rate Test
Find your display's true refresh rate — 60, 120, 144 or 240 Hz.
UFOGhosting Test
A UFO glides across your screen — see your panel's motion-blur trail.
▦Dead Pixel Test
Fullscreen colour screens that reveal dead, stuck and hot pixels.