Free CPU stress test that runs multi-threaded WebWorker busy loops (SHA-256 hashing) to load every logical core and report operations per second. Configurable thread count and duration. Includes thermal and browser-throttling warnings. Browser-based, no install.
Spawn up to navigator.hardwareConcurrency WebWorkers running a tight SHA-256 hashing loop. Each worker reports its ops/sec and the main thread sums them into a total. Adjust thread count and duration to stress-test thermals or just benchmark a machine — no install, runs entirely in your browser.
Stress settings
Warning: this test intentionally maxes your CPU. Expect fans to spin up and the machine to get warm. Laptops on battery may thermal-throttle within 30-60 seconds, which is itself a useful datapoint.
Live results
—Logical cores
0Total ops/sec
0Avg per thread
0Elapsed (s)
0Peak ops/sec
Was this tool helpful?Rate CPU Stress Test:4.9(9 ratings)Thanks for rating!
CPU Stress Test is a free, browser-based online utility that runs the full check instantly in your web browser.
Cost: Free, no signup
Install: None — runs in the browser
Privacy: Runs locally, no uploads
Platforms: Windows, macOS, Linux, Android, iOS
Time: Under a minute
Browser CPU Stress Test and Worker Throughput
Run a CPU stress test in the browser with a chosen number of workers and compare the reported work rate over time. The workload shares CPU resources with the browser, operating system and other apps, so its score is specific to this setup. Keep the run bounded and monitor system conditions separately; the page does not read CPU temperature or certify hardware stability.
What The Test Measures (And What It Doesn't)
This tool measures sustained integer throughput across multiple cores. It is a good proxy for workloads like compilation, compression, video encode, and 3D rendering — all of which are multi-threaded and compute-bound. It is a poor proxy for single-thread gaming performance, memory bandwidth, or GPU-bound work. For a comprehensive picture, pair this test with our GPU stress test (which exercises the graphics pipeline) and memory test (which tracks allocation and heap behavior). Numbers from this browser test are not directly comparable to native benchmarks like Cinebench or Geekbench, but they are comparable across runs on the same machine and browser, which is what matters for throttling detection.
Spotting Thermal And Power Throttling
For a separate build-planning estimate, check CPU and GPU balance at your intended resolution; the model does not diagnose the cause of a throughput drop in this stress test.
The single most informative pattern in this test is a full-speed burst followed by a sustained drop. A thin-and-light laptop will typically hold peak ops/sec for 20-40 seconds, then step down 30-50% as the CPU hits its thermal envelope. Desktop gaming rigs with good cooling should hold steady throughout. If you see throttling on a desktop, check: CPU cooler fans spinning, thermal paste age, case airflow, or an overclock that was stable on short benchmarks but falls over on sustained load. A freshly enabled EXPO/XMP memory profile counts as an overclock too — after switching it on per our DDR5 CL30 vs CL36 guide, a sustained run here is a quick first screen for gross instability. On laptops, plugging in vs battery makes a huge difference; "power saver" profiles cap clocks below thermal limits. If games stutter after long sessions, run the FPS test during a sustained load — a frame-rate drop that mirrors the ops/sec drop is a clear throttling signature.
Hybrid CPUs And Per-Thread Variance
On Intel 12th-gen and later, Apple Silicon (M1/M2/M3/M4), and various mobile SoCs, not all cores are equal. "Performance" cores (Intel P-cores, Apple P-cores) run at 3-5 GHz and handle heavy threads; "efficiency" cores (E-cores) run at 2-3 GHz and handle background work. When you spawn one worker per logical core, you will see the P-cores hitting 2-3× the ops/sec of the E-cores — that is working as designed. For the most useful benchmark of a hybrid CPU, limit threads to the P-core count and run again.
This page does not have a reliable hardware CPU-temperature reading. Use an appropriate system monitoring tool separately and stop a workload if the device becomes unstable or its normal thermal protections indicate a problem.
Is this a replacement for Prime95 or a full stability test?
No. A browser worker workload exercises a different path and is affected by scheduling and browser limits. A completed run does not certify every CPU instruction, memory path or overclock setting.
Can I compare scores from different browsers?
Treat those comparisons cautiously. Engine implementation, worker scheduling, power mode and background activity can change throughput. For a useful before-and-after comparison, keep the same browser, worker count and conditions.
Analyse high-pitched PC noise with your microphone. Compare a quiet baseline with normal PC activity and inspect frequency, tonal prominence and a live spectrum.
01 / 10DDR5 buying mathPay $120 more for 2 nanoseconds?CL30 vs CL36 looks big on the box. The real difference is 2 nanoseconds.02 / 10What CL really isCAS latency counts cycles, not timeCL is how many clock ticks the RAM waits before answering. Ticks get faster with speed.03 / 10The one-line formulans = 2000 x CL / MT/sTrue latency in nanoseconds. DDR5-6000 CL30: 2000 x 30 / 6000 = 10.0 ns.04 / 10CL30 vs CL36 at 600010.0 ns versus 12.0 nsSame speed, different CL: the whole debate is about 2 nanoseconds of wait time.05 / 10The tie surprise7200 CL36 is also 10.0 nsSo is 6400 CL32. A higher CL on a faster kit can match a lower CL exactly.06 / 10What 2 ns buys in gamesRoughly 1-4% average FPSOnly when CPU-bound, and benchmarks disagree. Smoother 1% lows are the steadier win.07 / 10Price check, Aug 11, 2026The CL30 premium: $120G.Skill CL30 $599.99 vs CL36 $479.99. A Patriot CL30 kit: $429.99. Shop across brands.08 / 10The EXPO/XMP gotchaYour CL30 may be running CL40Kits boot at JEDEC defaults until you enable EXPO or XMP in BIOS. Check yours today.09 / 10The X3D exceptionBig cache blunts CLOn 7800X3D-class CPUs, the stacked cache blunts CL gains. Buy CL36 and save.10 / 10The verdictSmall delta: yes. Upgrade: no.Compare your two kits in real nanoseconds - presets loaded, math done for you.
01 / 10Phone vibration testYour phone stopped buzzingBefore you book a repair, find out whether it is the motor or just a setting.02 / 10The symptomMissed calls and silent alertsA dead motor is easy to miss. You only notice the calls you never felt arrive.03 / 10What is insideA tiny weight on a motorMost phones spin an offset weight or drive a linear actuator to make the buzz.04 / 10Check this firstSettings fake a dead motorSilent mode, Do Not Disturb and per-app vibration all switch the buzz off.05 / 10Run the testOne tap, three patternsThe browser asks the phone to vibrate in short, long and pulsed patterns.06 / 10Result: weakYou feel it, but barelyA faint buzz often means a loose motor mount or a case damping the vibration.07 / 10Result: nothingNo buzz on any patternWith settings ruled out, silence points at the motor or its connector.08 / 10Result: on and offIt works, then it does notIntermittent buzzing usually means a failing solder joint or a worn motor.09 / 10One honest limitiPhones cannot run this testSafari on iOS does not support the browser vibration API, so use Android.10 / 10Your turnFind out in thirty secondsRun the three patterns, then decide whether it is a setting or the hardware.