| | | | | | |

Core i3-10105 vs Ryzen 9 3900X


Description
The i3-10105 is based on Comet Lake architecture while the 3900X is based on Zen 2.

Using the multithread performance as a reference, the i3-10105 gets a score of 253.9 k points while the 3900X gets 756.3 k points.

Summarizing, the 3900X is 3 times faster than the i3-10105. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
a0653
870f10
Core
Comet Lake-S
Matisse
Architecture
Base frecuency
3.7 GHz
3.8 GHz
Boost frecuency
4.4 GHz
4.6 GHz
Socket
LGA 1200
AM4
Cores/Threads
4/8
12/24
TDP
65 W
105 W
Cache L1 (d+i)
4x32+4x32 kB
12x32+12x32 kB
Cache L2
4x256 kB
12x512 kB
Cache L3
6144 kB
4x16384 kB
Date
March 2021
July 2019
Mean monothread perf.
68.92k points
72.51k points
Mean multithread perf.
253.93k 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
i3-10105
3900X
Test#1 (Integers)
4.5k
4.46k (x0.99)
Test#2 (FP)
18.39k
18.46k (x1)
Test#3 (Generic, ZIP)
5.78k
8.05k (x1.39)
Test#1 (Memory)
8.3k
23.71k (x2.85)
TOTAL
36.97k
54.68k (x1.48)

Multithread

i3-10105

3900X
Test#1 (Integers)
16.13k
52.65k (x3.26)
Test#2 (FP)
75.62k
265.41k (x3.51)
Test#3 (Generic, ZIP)
27.88k
140.78k (x5.05)
Test#1 (Memory)
3.57k
46.91k (x13.13)
TOTAL
123.2k
505.76k (x4.11)

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
i3-10105
3900X
Test#1 (Integers)
16.19k
17.35k (x1.07)
Test#2 (FP)
23.07k
25.87k (x1.12)
Test#3 (Generic, ZIP)
6.04k
8.72k (x1.44)
Test#1 (Memory)
8.46k
27.86k (x3.29)
TOTAL
53.77k
79.8k (x1.48)

Multithread

i3-10105

3900X
Test#1 (Integers)
57.59k
201.57k (x3.5)
Test#2 (FP)
100.63k
284.41k (x2.83)
Test#3 (Generic, ZIP)
28.59k
145.16k (x5.08)
Test#1 (Memory)
3.56k
100.56k (x28.27)
TOTAL
190.38k
731.7k (x3.84)

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
i3-10105
3900X
Test#1 (Integers)
16.11k
16.95k (x1.05)
Test#2 (FP)
24.12k
25.37k (x1.05)
Test#3 (Generic, ZIP)
5.71k
9.23k (x1.62)
Test#1 (Memory)
7.89k
24.83k (x3.15)
TOTAL
53.83k
76.38k (x1.42)

Multithread

i3-10105

3900X
Test#1 (Integers)
58.25k
196.31k (x3.37)
Test#2 (FP)
105.73k
290.5k (x2.75)
Test#3 (Generic, ZIP)
27.8k
143.95k (x5.18)
Test#1 (Memory)
3.51k
64.92k (x18.52)
TOTAL
195.29k
695.69k (x3.56)

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
i3-10105
3900X
Test#1 (Integers)
28.9k
16.73k (x0.58)
Test#2 (FP)
25.85k
24.74k (x0.96)
Test#3 (Generic, ZIP)
5.88k
8.82k (x1.5)
Test#1 (Memory)
8.29k
22.22k (x2.68)
TOTAL
68.92k
72.51k (x1.05)

Multithread

i3-10105

3900X
Test#1 (Integers)
111.69k
248.24k (x2.22)
Test#2 (FP)
110.23k
309.66k (x2.81)
Test#3 (Generic, ZIP)
28.45k
140.01k (x4.92)
Test#1 (Memory)
3.56k
58.39k (x16.42)
TOTAL
253.93k
756.3k (x2.98)

Performance/W
i3-10105
3900X
Test#1 (Integers)
1718 points/W
2364 points/W
Test#2 (FP)
1696 points/W
2949 points/W
Test#3 (Generic, ZIP)
438 points/W
1333 points/W
Test#1 (Memory)
55 points/W
556 points/W
TOTAL
3907 points/W
7203 points/W

Performance/GHz
i3-10105
3900X
Test#1 (Integers)
6568 points/GHz
3638 points/GHz
Test#2 (FP)
5876 points/GHz
5377 points/GHz
Test#3 (Generic, ZIP)
1337 points/GHz
1917 points/GHz
Test#1 (Memory)
1883 points/GHz
4831 points/GHz
TOTAL
15664 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