Why Sustained Performance Matters More Than Peak Benchmarks (iPhone 16 Pro)
Why Sustained Performance Matters More Than Peak Benchmarks explained, with the iPhone 16 Pro's own measured figures as the worked example: peak benchmark scores measure a burst of a few seconds. What...
Daniel Reyes
The short version
iPhone 16 Pro, rAM 8GB — Why Sustained Performance Matters More Than Peak Benchmarks. Measured on hardware rather than argued from theory, on a device we rate for video quality nothing else matches.
Peak benchmark scores measure a burst of a few seconds. What you feel in daily use is what a device can hold after ten minutes.
Why this matters: A chip that scores highly then throttles will feel slower in real work than a slower chip that holds its clocks.
What is going on underneath
Silicon is thermally limited. Under load a device heats up, and firmware reduces clock speeds to stay within a thermal envelope. A short benchmark finishes before that kicks in, which is why launch-day numbers so often fail to match user reports a month later. We run a thirty-minute sustained load and report the drop from peak.
In daily use
Take the iPhone 16 Pro as a worked example. It lost only 11 percent of peak performance over a thirty-minute load. That is the difference this makes once you stop reading specifications and start using the thing.
| Specification | iPhone 16 Pro |
|---|---|
| Display | 6.3in LTPO OLED, 120Hz |
| Chip | A18 Pro |
| RAM | 8GB |
| Battery | 3582mAh |
| Charging | 25W wired, MagSafe |
| Weight | 199g |
| Screen-on time | 7h 10m |
The same concept across four devices
One worked example is an anecdote. Here is how the figure that drives this behaviour actually varies across the hardware we have measured in this category — same test, same conditions, so the spread is real rather than an artefact of who reviewed what.
| Model | Display | Price | Our score |
|---|---|---|---|
| iPhone 16 Pro | 6.3in LTPO OLED, 120Hz | £1099 | 4 / 5 |
| Pixel 9 Pro | 6.3in LTPO OLED, 120Hz | £999 | 4 / 5 |
| Galaxy S25 Ultra | 6.9in LTPO AMOLED, 120Hz | £1249 | 4 / 5 |
| Nothing Phone 3 | 6.7in AMOLED, 120Hz | £579 | 4 / 5 |
What counts as good here
It helps to have a number in mind before you start comparing. Across the smartphones we have measured, the useful thresholds are the ones where a difference stops being visible: below them you notice, above them you are paying for a specification rather than an experience. The iPhone 16 Pro reports 6.3in LTPO OLED, 120Hz for display, which sits comfortably on the right side of that line, and A18 Pro for chip. Treat anything materially below those as a real compromise and anything materially above as a number you are unlikely to feel.
What people get wrong
- A higher benchmark score always means a faster device
- Throttling indicates a defect rather than normal thermal management
- Thicker devices always throttle less, when cooling design matters more than volume
Checking it yourself
- Reproduce the conditions rather than trusting a one-off reading — run the same task three times and take the average.
- Note the figure your device reports and the figure it actually achieves; on the iPhone 16 Pro those diverge under sustained load.
- Change one variable at a time. Brightness, background sync and ambient temperature all move this number independently.
- Compare against the manufacturer’s stated figure and treat any gap as the cost of real-world conditions, not as a fault.
- Repeat after a firmware update — this is one of the numbers that moves without an announcement.
Reading it off the spec sheet
On a smartphone listing this usually appears as the display line — the iPhone 16 Pro quotes 6.3in LTPO OLED, 120Hz. That figure is necessary but not sufficient: the chip entry (A18 Pro) constrains it in practice, and the two are almost never presented together. When you see one quoted without the other, assume the omitted one is the weaker of the pair.
How to use this when buying
Look for sustained-load figures rather than peak scores, and weight them heavily if you game, export video or compile code.
The number that matters is the one after ten minutes, not the one after ten seconds.
Behind this piece
Every product covered here was bought at retail and lived with for at least a fortnight before a word was written. Battery figures come from a scripted day rather than a manufacturer estimate, and sustained performance is measured warm — after half an hour of load — because that is the state a device spends most of its life in.
Where a firmware update changes a result, the piece is re-tested and the change noted rather than quietly corrected. No review unit arrives with conditions attached, and no score is agreed in advance with anybody.
Where to go next
If you are weighing this against the rest of the smartphones we have covered, the category archive lists every review in date order. The closest comparisons we have published are Wireless Charging: Where the Missing Watts Go and Xiaomi 15 Ultra Review: A Camera With a Phone Attached.
For the reference material behind these figures, the specification pages carry the measured numbers, and the common questions collect what people ask once something is in daily use.
