| | | | | | |

Core i3-10105 vs Ryzen 5 3500U


Description
The i3-10105 is based on Comet Lake architecture while the 3500U is based on Zen+.

Using the multithread performance as a reference, the i3-10105 gets a score of 253.9 k points while the 3500U gets 141 k points.

Summarizing, the i3-10105 is 1.8 times faster than the 3500U. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
a0653
810f81
Core
Comet Lake-S
Picasso
Architecture
Base frecuency
3.7 GHz
2.1 GHz
Boost frecuency
4.4 GHz
3.7 GHz
Socket
LGA 1200
BGA-FP5
Cores/Threads
4/8
4/8
TDP
65 W
15 W
Cache L1 (d+i)
4x32+4x32 kB
4x64+6x32 kB
Cache L2
4x256 kB
4x512 kB
Cache L3
6144 kB
4096 kB
Date
March 2021
January 2019
Mean monothread perf.
68.92k points
36.64k points
Mean multithread perf.
253.93k points
140.97k 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
3500U
Test#1 (Integers)
4.5k
3.24k (x0.72)
Test#2 (FP)
18.39k
13.16k (x0.72)
Test#3 (Generic, ZIP)
5.78k
4.41k (x0.76)
Test#1 (Memory)
8.3k
3.32k (x0.4)
TOTAL
36.97k
24.12k (x0.65)

Multithread

i3-10105

3500U
Test#1 (Integers)
16.13k
12.95k (x0.8)
Test#2 (FP)
75.62k
57.84k (x0.76)
Test#3 (Generic, ZIP)
27.88k
21.05k (x0.76)
Test#1 (Memory)
3.57k
3.51k (x0.98)
TOTAL
123.2k
95.36k (x0.77)

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
3500U
Test#1 (Integers)
16.19k
11.98k (x0.74)
Test#2 (FP)
23.07k
15.85k (x0.69)
Test#3 (Generic, ZIP)
6.04k
4.53k (x0.75)
Test#1 (Memory)
8.46k
3.29k (x0.39)
TOTAL
53.77k
35.65k (x0.66)

Multithread

i3-10105

3500U
Test#1 (Integers)
57.59k
48.28k (x0.84)
Test#2 (FP)
100.63k
74.19k (x0.74)
Test#3 (Generic, ZIP)
28.59k
23.29k (x0.81)
Test#1 (Memory)
3.56k
3.47k (x0.97)
TOTAL
190.38k
149.23k (x0.78)

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
3500U
Test#1 (Integers)
16.11k
11.1k (x0.69)
Test#2 (FP)
24.12k
18.97k (x0.79)
Test#3 (Generic, ZIP)
5.71k
3.9k (x0.68)
Test#1 (Memory)
7.89k
3.39k (x0.43)
TOTAL
53.83k
37.37k (x0.69)

Multithread

i3-10105

3500U
Test#1 (Integers)
58.25k
45.74k (x0.79)
Test#2 (FP)
105.73k
75.47k (x0.71)
Test#3 (Generic, ZIP)
27.8k
21.89k (x0.79)
Test#1 (Memory)
3.51k
3.49k (x1)
TOTAL
195.29k
146.6k (x0.75)

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
3500U
Test#1 (Integers)
28.9k
10.88k (x0.38)
Test#2 (FP)
25.85k
18.09k (x0.7)
Test#3 (Generic, ZIP)
5.88k
4.29k (x0.73)
Test#1 (Memory)
8.29k
3.36k (x0.41)
TOTAL
68.92k
36.64k (x0.53)

Multithread

i3-10105

3500U
Test#1 (Integers)
111.69k
42.44k (x0.38)
Test#2 (FP)
110.23k
73.82k (x0.67)
Test#3 (Generic, ZIP)
28.45k
20.76k (x0.73)
Test#1 (Memory)
3.56k
3.96k (x1.11)
TOTAL
253.93k
140.97k (x0.56)

Performance/W
i3-10105
3500U
Test#1 (Integers)
1718 points/W
2829 points/W
Test#2 (FP)
1696 points/W
4921 points/W
Test#3 (Generic, ZIP)
438 points/W
1384 points/W
Test#1 (Memory)
55 points/W
264 points/W
TOTAL
3907 points/W
9398 points/W

Performance/GHz
i3-10105
3500U
Test#1 (Integers)
6568 points/GHz
2942 points/GHz
Test#2 (FP)
5876 points/GHz
4890 points/GHz
Test#3 (Generic, ZIP)
1337 points/GHz
1161 points/GHz
Test#1 (Memory)
1883 points/GHz
909 points/GHz
TOTAL
15664 points/GHz
9901 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