| | | | | | |

Core i5-10500 vs i5-3570K


Description
The i5-10500 is based on Comet Lake architecture while the i5-3570K is based on Ivy Bridge.

Using the multithread performance as a reference, the i5-10500 gets a score of 297.9 k points while the i5-3570K gets 120.2 k points.

Summarizing, the i5-10500 is 2.5 times faster than the i5-3570K . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
a0653
306a9
Core
Comet Lake-S
Ivy Bridge
Architecture
Base frecuency
3.1 GHz
3.4 GHz
Boost frecuency
4.5 GHz
3.8 GHz
Socket
FC-LGA 1200
LGA 1155
Cores/Threads
6/12
4/4
TDP
65 W
77 W
Cache L1 (d+i)
6x32+6x32 kB
4x32+x4x32 kB
Cache L2
6x256 kB
4x256 kB
Cache L3
12288 kB
6144 kB
Date
April 2020
April 2012
Mean monothread perf.
75.27k points
34.57k points
Mean multithread perf.
387.99k points
120.16k 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
i5-10500
i5-3570K
Test#1 (Integers)
4.52k
3.85k (x0.85)
Test#2 (FP)
18.52k
10.72k (x0.58)
Test#3 (Generic, ZIP)
5.58k
4.83k (x0.87)
Test#1 (Memory)
14.2k
5.21k (x0.37)
TOTAL
42.82k
24.6k (x0.57)

Multithread

i5-10500

i5-3570K
Test#1 (Integers)
25.26k
14.34k (x0.57)
Test#2 (FP)
120.48k
40.2k (x0.33)
Test#3 (Generic, ZIP)
38.12k
17.91k (x0.47)
Test#1 (Memory)
7.68k
7.05k (x0.92)
TOTAL
191.54k
79.5k (x0.42)

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
i5-10500
i5-3570K
Test#1 (Integers)
16.3k
12.78k (x0.78)
Test#2 (FP)
23.22k
11.69k (x0.5)
Test#3 (Generic, ZIP)
6.22k
5.01k (x0.81)
Test#1 (Memory)
14.05k
5.19k (x0.37)
TOTAL
59.79k
34.66k (x0.58)

Multithread

i5-10500

i5-3570K
Test#1 (Integers)
92.61k
48.18k (x0.52)
Test#2 (FP)
147.68k
43.19k (x0.29)
Test#3 (Generic, ZIP)
40.71k
18.37k (x0.45)
Test#1 (Memory)
7.78k
7.03k (x0.9)
TOTAL
288.77k
116.78k (x0.4)

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
i5-10500
i5-3570K
Test#1 (Integers)
16.33k
12.55k (x0.77)
Test#2 (FP)
24.73k
12.14k (x0.49)
Test#3 (Generic, ZIP)
5.99k
4.9k (x0.82)
Test#1 (Memory)
13.64k
4.98k (x0.37)
TOTAL
60.69k
34.57k (x0.57)

Multithread

i5-10500

i5-3570K
Test#1 (Integers)
91.64k
47.53k (x0.52)
Test#2 (FP)
158.71k
46.16k (x0.29)
Test#3 (Generic, ZIP)
39.84k
18.36k (x0.46)
Test#1 (Memory)
7.76k
8.1k (x1.04)
TOTAL
297.94k
120.16k (x0.4)

Performance/W
i5-10500
i5-3570K
Test#1 (Integers)
1410 points/W
617 points/W
Test#2 (FP)
2442 points/W
599 points/W
Test#3 (Generic, ZIP)
613 points/W
238 points/W
Test#1 (Memory)
119 points/W
105 points/W
TOTAL
4584 points/W
1560 points/W

Performance/GHz
i5-10500
i5-3570K
Test#1 (Integers)
3629 points/GHz
3303 points/GHz
Test#2 (FP)
5496 points/GHz
3194 points/GHz
Test#3 (Generic, ZIP)
1332 points/GHz
1288 points/GHz
Test#1 (Memory)
3031 points/GHz
1310 points/GHz
TOTAL
13487 points/GHz
9096 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