| | | | | | |

Core i5-3570K vs i5-10500


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

Using the multithread performance as a reference, the i5-3570K gets a score of 120.2 k points while the i5-10500 gets 297.9 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
306a9
a0653
Core
Ivy Bridge
Comet Lake-S
Architecture
Base frecuency
3.4 GHz
3.1 GHz
Boost frecuency
3.8 GHz
4.5 GHz
Socket
LGA 1155
FC-LGA 1200
Cores/Threads
4/4
6/12
TDP
77 W
65 W
Cache L1 (d+i)
4x32+x4x32 kB
6x32+6x32 kB
Cache L2
4x256 kB
6x256 kB
Cache L3
6144 kB
12288 kB
Date
April 2012
April 2020
Mean monothread perf.
34.57k points
75.27k points
Mean multithread perf.
120.16k points
387.99k 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
i5-3570K
i5-10500
Test#1 (Integers)
3.85k
4.52k (x1.17)
Test#2 (FP)
10.72k
18.52k (x1.73)
Test#3 (Generic, ZIP)
4.83k
5.58k (x1.15)
Test#1 (Memory)
5.21k
14.2k (x2.73)
TOTAL
24.6k
42.82k (x1.74)

Multithread

i5-3570K

i5-10500
Test#1 (Integers)
14.34k
25.26k (x1.76)
Test#2 (FP)
40.2k
120.48k (x3)
Test#3 (Generic, ZIP)
17.91k
38.12k (x2.13)
Test#1 (Memory)
7.05k
7.68k (x1.09)
TOTAL
79.5k
191.54k (x2.41)

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
i5-3570K
i5-10500
Test#1 (Integers)
12.78k
16.3k (x1.28)
Test#2 (FP)
11.69k
23.22k (x1.99)
Test#3 (Generic, ZIP)
5.01k
6.22k (x1.24)
Test#1 (Memory)
5.19k
14.05k (x2.71)
TOTAL
34.66k
59.79k (x1.72)

Multithread

i5-3570K

i5-10500
Test#1 (Integers)
48.18k
92.61k (x1.92)
Test#2 (FP)
43.19k
147.68k (x3.42)
Test#3 (Generic, ZIP)
18.37k
40.71k (x2.22)
Test#1 (Memory)
7.03k
7.78k (x1.11)
TOTAL
116.78k
288.77k (x2.47)

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
i5-3570K
i5-10500
Test#1 (Integers)
12.55k
16.33k (x1.3)
Test#2 (FP)
12.14k
24.73k (x2.04)
Test#3 (Generic, ZIP)
4.9k
5.99k (x1.22)
Test#1 (Memory)
4.98k
13.64k (x2.74)
TOTAL
34.57k
60.69k (x1.76)

Multithread

i5-3570K

i5-10500
Test#1 (Integers)
47.53k
91.64k (x1.93)
Test#2 (FP)
46.16k
158.71k (x3.44)
Test#3 (Generic, ZIP)
18.36k
39.84k (x2.17)
Test#1 (Memory)
8.1k
7.76k (x0.96)
TOTAL
120.16k
297.94k (x2.48)

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

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