| | | | | | |

Core i5-12500H vs Ryzen 9 3900X


Description
The i5-12500H is based on Alder Lake architecture while the 3900X is based on Zen 2.

Using the multithread performance as a reference, the i5-12500H gets a score of 225.7 k points while the 3900X gets 756.3 k points.

Summarizing, the 3900X is 3.4 times faster than the i5-12500H. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
906a3
870f10
Core
Alder Lake-H
Matisse
Architecture
Base frecuency
2.5 GHz
3.8 GHz
Boost frecuency
4.5 GHz
4.6 GHz
Socket
BGA 1744
AM4
Cores/Threads
12/16
12/24
TDP
45 W
105 W
Cache L1 (d+i)
4x32/8X64+4x48/8X32 kB
12x32+12x32 kB
Cache L2
4x1280/2x2048 kB
12x512 kB
Cache L3
18432 kB
4x16384 kB
Date
February 2022
July 2019
Mean monothread perf.
58.37k points
72.51k points
Mean multithread perf.
225.65k points
756.3k points

Non-optimized benchmark
The benchmark in Mode 0 (FPU) measures cpu performance with non-optimized software. It uses the basic µinstructions from the i386 architecture with the i387 floating point unit. This mode is compatible with all CPUs so it's practical to compare very different CPUs
Monothread
i5-12500H
3900X
Test#1 (Integers)
6.93k
4.46k (x0.64)
Test#2 (FP)
18.76k
18.46k (x0.98)
Test#3 (Generic, ZIP)
9.46k
8.05k (x0.85)
Test#1 (Memory)
8.17k
23.71k (x2.9)
TOTAL
43.33k
54.68k (x1.26)

Multithread

i5-12500H

3900X
Test#1 (Integers)
18.04k
52.65k (x2.92)
Test#2 (FP)
66.78k
265.41k (x3.97)
Test#3 (Generic, ZIP)
37.55k
140.78k (x3.75)
Test#1 (Memory)
6.08k
46.91k (x7.72)
TOTAL
128.45k
505.76k (x3.94)

SSE3 optimized benchmark
The benchmark in mode I (SSE) is optimized for the use of SIMD instructions with 128 bits register and the SSE set up to version 3. Nearly every modern CPU has support for this mode.
Monothread
i5-12500H
3900X
Test#1 (Integers)
21.93k
17.35k (x0.79)
Test#2 (FP)
18.79k
25.87k (x1.38)
Test#3 (Generic, ZIP)
10.5k
8.72k (x0.83)
Test#1 (Memory)
8.11k
27.86k (x3.44)
TOTAL
59.33k
79.8k (x1.35)

Multithread

i5-12500H

3900X
Test#1 (Integers)
61.07k
201.57k (x3.3)
Test#2 (FP)
86.08k
284.41k (x3.3)
Test#3 (Generic, ZIP)
41.08k
145.16k (x3.53)
Test#1 (Memory)
6.02k
100.56k (x16.71)
TOTAL
194.25k
731.7k (x3.77)

AVX optimized benchmark
The benchmark in mode II (AVX) is optimized to used 256 bits registers beside the first version of the Advanced Vector Extensions (AVX). The first AVX compatible CPU was released in 2011.
Monothread
i5-12500H
3900X
Test#1 (Integers)
21.11k
16.95k (x0.8)
Test#2 (FP)
19.61k
25.37k (x1.29)
Test#3 (Generic, ZIP)
9.53k
9.23k (x0.97)
Test#1 (Memory)
7.72k
24.83k (x3.22)
TOTAL
57.97k
76.38k (x1.32)

Multithread

i5-12500H

3900X
Test#1 (Integers)
61.44k
196.31k (x3.2)
Test#2 (FP)
93.66k
290.5k (x3.1)
Test#3 (Generic, ZIP)
40.09k
143.95k (x3.59)
Test#1 (Memory)
6.01k
64.92k (x10.8)
TOTAL
201.2k
695.69k (x3.46)

AVX2 optimized benchmark
The benchmark in mode III (AVX2), like AVX1, is optimized to used 256 bits registers beside the second version of the Advanced Vector Extensions (AVX). The first AVX2 compatible CPU was released in 2013.
Monothread
i5-12500H
3900X
Test#1 (Integers)
22.61k
16.73k (x0.74)
Test#2 (FP)
17.73k
24.74k (x1.4)
Test#3 (Generic, ZIP)
9.63k
8.82k (x0.92)
Test#1 (Memory)
8.4k
22.22k (x2.64)
TOTAL
58.37k
72.51k (x1.24)

Multithread

i5-12500H

3900X
Test#1 (Integers)
85.49k
248.24k (x2.9)
Test#2 (FP)
94.93k
309.66k (x3.26)
Test#3 (Generic, ZIP)
39.15k
140.01k (x3.58)
Test#1 (Memory)
6.08k
58.39k (x9.61)
TOTAL
225.65k
756.3k (x3.35)

Performance/W
i5-12500H
3900X
Test#1 (Integers)
1900 points/W
2364 points/W
Test#2 (FP)
2110 points/W
2949 points/W
Test#3 (Generic, ZIP)
870 points/W
1333 points/W
Test#1 (Memory)
135 points/W
556 points/W
TOTAL
5014 points/W
7203 points/W

Performance/GHz
i5-12500H
3900X
Test#1 (Integers)
5025 points/GHz
3638 points/GHz
Test#2 (FP)
3939 points/GHz
5377 points/GHz
Test#3 (Generic, ZIP)
2139 points/GHz
1917 points/GHz
Test#1 (Memory)
1867 points/GHz
4831 points/GHz
TOTAL
12971 points/GHz
15763 points/GHz

Monothread performance graph
Monothread performance graphics gives the performance vs time. They are useful to measure the time it takes to the CPU to reach the maximum performance.

Usually, CPU's performance will be steady during these tests but if it has a slow frequency strategy, the first samples will show a lower score.


Test#1 (Integers) [points vs time]

grafica bm.hardlimit.com


Test#2 (FP) [points vs time]

grafica bm.hardlimit.com


Test#3 (Generic, ZIP) [points vs time]

grafica bm.hardlimit.com


Test#1 (Memory) [points vs time]

grafica bm.hardlimit.com

Multithread performance graph
Multithread graphs measure the performance against a heavy load during certain time.

If CPU's TDP doesn't limit the frequency and the machine is properly cooled, performance should remain steady vs time. Otherwise, the performance score will oscillate or decrease over time.


Test#1 (Integers) [points vs time]

grafica bm.hardlimit.com


Test#2 (FP) [points vs time]

grafica bm.hardlimit.com


Test#3 (Generic, ZIP) [points vs time]

grafica bm.hardlimit.com


Test#1 (Memory) [points vs time]

grafica bm.hardlimit.com

Hardlimit Benchmark Central - Ver. 3.11.4