Sysbench test was run on two types of AWS EC2 instances t3.medium (x86-64) and t4g.medium (ARM). The command was executed with the parameters sysbench --test=cpu run.

t3.medium:

sysbench 1.0.18 (using system LuaJIT 2.1.0-beta3)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time


Prime numbers limit: 10000

Initializing worker threads...

Threads started!

CPU speed:
    events per second:   984.07

General statistics:
    total time:                          10.0008s
    total number of events:              9843

Latency (ms):
         min:                                    0.94
         avg:                                    1.02
         max:                                    8.81
         95th percentile:                        1.06
         sum:                                 9995.26

Threads fairness:
    events (avg/stddev):           9843.0000/0.00
    execution time (avg/stddev):   9.9953/0.00

t4g.medium:

sysbench 1.0.20 (using system LuaJIT 2.1.0-beta3)

Running the test with following options:
Number of threads: 1
Initializing random number generator from current time


Prime numbers limit: 10000

Initializing worker threads...

Threads started!

CPU speed:
    events per second:  2807.81

General statistics:
    total time:                          10.0004s
    total number of events:              28083

Latency (ms):
         min:                                    0.35
         avg:                                    0.36
         max:                                    0.43
         95th percentile:                        0.36
         sum:                                 9995.59

Threads fairness:
    events (avg/stddev):           28083.0000/0.00
    execution time (avg/stddev):   9.9956/0.00