In short, cheating behavior was clear and demonstrable by both looking at score variance, and by monitoring CPU frequencies throughout the benchmark, which showed a frequency floor that - for the most part - allowed the device to consistently score closer to its full potential. This minimum frequency reduced the effective frequency range, which in turn reduced the number of step frequencies in benchmarks, this resulted in slightly lower variance and, as we showed, higher sustained performance as the higher minimum frequency could not be overridden by thermal throttling. Then, the ROM would alter the frequency in relation to an adjusted CPU load - our tools showed CPU load would drop to 0 percent regardless of obvious activity within the application, and the CPU would see a near-minimum frequency of 1.29GHz in the big cores and 0.98GHz in the little cores. Such application names were explicitly listed by their package IDs within the ROM in a manifest that specified the targets. Last time around, OnePlus introduced changes to the behavior of their ROM whenever it detected a benchmark application was opened. The site explains how the cheating that has been detected in the OnePlus 5 differs from the technique used in the OnePlus 3T:
It also affects a large number of well-known benchmarking tools: AnTuTu, Androbench, Geekbench 4, GFXBench, Quadrant, Nenamark 2, and Vellamo. While with the OnePlus 3T things were somewhat subtle, this time around it appears to be more blatant. Just as before, XDA Developers found that OxygenOS - the OnePlus take on Android - was gaming benchmarks.