| | | | | | |

Core i5-6500 vs i3-7100


Description
The i5-6500 is based on Skylake architecture while the i3-7100 is based on Kaby Lake.

Using the multithread performance as a reference, the i5-6500 gets a score of 179.4 k points while the i3-7100 gets 124.8 k points.

Summarizing, the i5-6500 is 1.4 times faster than the i3-7100. To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
506e3
906e9
Core
Skylake-S
Kaby Lake-S
Architecture
Base frecuency
3.2 GHz
3.9 GHz
Boost frecuency
3.6 GHz
3.9 GHz
Socket
LGA 1151
LGA 1151
Cores/Threads
4/4
2/4
TDP
65 W
51 W
Cache L1 (d+i)
4x32+4x32 kB
2x32+2x32 kB
Cache L2
4x256 kB
2x256 kB
Cache L3
6144 kB
3072 kB
Date
September 2015
January 2017
Mean monothread perf.
53.7k points
57.86k points
Mean multithread perf.
179.44k points
124.8k 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
i5-6500
i3-7100
Test#1 (Integers)
3.46k
4.01k (x1.16)
Test#2 (FP)
14.61k
16.38k (x1.12)
Test#3 (Generic, ZIP)
4.66k
5.31k (x1.14)
Test#1 (Memory)
6.99k
3.98k (x0.57)
TOTAL
29.71k
29.69k (x1)

Multithread

i5-6500

i3-7100
Test#1 (Integers)
12.52k
8.1k (x0.65)
Test#2 (FP)
51.13k
38.7k (x0.76)
Test#3 (Generic, ZIP)
17.41k
12.69k (x0.73)
Test#1 (Memory)
3.9k
3.76k (x0.96)
TOTAL
84.96k
63.24k (x0.74)

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
i5-6500
i3-7100
Test#1 (Integers)
13.07k
14.41k (x1.1)
Test#2 (FP)
20.23k
22.38k (x1.11)
Test#3 (Generic, ZIP)
4.93k
5.45k (x1.11)
Test#1 (Memory)
9.2k
4.96k (x0.54)
TOTAL
47.43k
47.21k (x1)

Multithread

i5-6500

i3-7100
Test#1 (Integers)
49.62k
30.48k (x0.61)
Test#2 (FP)
74.82k
52.08k (x0.7)
Test#3 (Generic, ZIP)
18.46k
12.97k (x0.7)
Test#1 (Memory)
4.21k
4.56k (x1.08)
TOTAL
147.12k
100.1k (x0.68)

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
i5-6500
i3-7100
Test#1 (Integers)
22.89k
25.53k (x1.12)
Test#2 (FP)
19.87k
22.98k (x1.16)
Test#3 (Generic, ZIP)
4.58k
5.37k (x1.17)
Test#1 (Memory)
6.36k
3.97k (x0.62)
TOTAL
53.7k
57.86k (x1.08)

Multithread

i5-6500

i3-7100
Test#1 (Integers)
84.36k
54.73k (x0.65)
Test#2 (FP)
72.91k
53.55k (x0.73)
Test#3 (Generic, ZIP)
16.08k
12.93k (x0.8)
Test#1 (Memory)
6.1k
3.6k (x0.59)
TOTAL
179.44k
124.8k (x0.7)

Performance/W
i5-6500
i3-7100
Test#1 (Integers)
1298 points/W
1073 points/W
Test#2 (FP)
1122 points/W
1050 points/W
Test#3 (Generic, ZIP)
247 points/W
254 points/W
Test#1 (Memory)
94 points/W
71 points/W
TOTAL
2761 points/W
2447 points/W

Performance/GHz
i5-6500
i3-7100
Test#1 (Integers)
6359 points/GHz
6547 points/GHz
Test#2 (FP)
5521 points/GHz
5893 points/GHz
Test#3 (Generic, ZIP)
1271 points/GHz
1377 points/GHz
Test#1 (Memory)
1766 points/GHz
1019 points/GHz
TOTAL
14917 points/GHz
14836 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