| | | | | | |

Core i5-3470 vs i5-10400T


Description
The i5-3470 is based on Ivy Bridge architecture while the i5-10400T is based on Comet Lake.

Using the multithread performance as a reference, the i5-3470 gets a score of 94.1 k points while the i5-10400T gets 235.8 k points.

Summarizing, the i5-10400T is 2.5 times faster than the i5-3470 . 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
3.2 GHz
2 GHz
Boost frecuency
3.6 GHz
3.6 GHz
Socket
LGA 1155
FC-LGA 1200
Cores/Threads
4/4
6/12
TDP
77 W
35 W
Cache L1 (d+i)
4x32+4x32 kB
6x32+6x32 kB
Cache L2
4x256 kB
6x256 kB
Cache L3
6144 kB
12288 kB
Date
June 2012
April 2020
Mean monothread perf.
31.71k points
57.85k points
Mean multithread perf.
94.15k points
307.18k 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
i5-3470
i5-10400T
Test#1 (Integers)
3.62k
4k (x1.11)
Test#2 (FP)
10.08k
14.19k (x1.41)
Test#3 (Generic, ZIP)
4.47k
4.62k (x1.03)
Test#1 (Memory)
5.39k
11.03k (x2.05)
TOTAL
23.56k
33.84k (x1.44)

Multithread

i5-3470

i5-10400T
Test#1 (Integers)
13.66k
22.77k (x1.67)
Test#2 (FP)
37.73k
96.59k (x2.56)
Test#3 (Generic, ZIP)
17.07k
31.65k (x1.85)
Test#1 (Memory)
8.57k
2.45k (x0.29)
TOTAL
77.04k
153.46k (x1.99)

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
i5-3470
i5-10400T
Test#1 (Integers)
12.26k
12.61k (x1.03)
Test#2 (FP)
11k
17.94k (x1.63)
Test#3 (Generic, ZIP)
4.76k
4.83k (x1.01)
Test#1 (Memory)
5.39k
10.81k (x2)
TOTAL
33.42k
46.19k (x1.38)

Multithread

i5-3470

i5-10400T
Test#1 (Integers)
46.54k
74.62k (x1.6)
Test#2 (FP)
41.4k
119.63k (x2.89)
Test#3 (Generic, ZIP)
18.09k
32.65k (x1.8)
Test#1 (Memory)
8.69k
2.52k (x0.29)
TOTAL
114.73k
229.42k (x2)

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
i5-3470
i5-10400T
Test#1 (Integers)
11.51k
12.5k (x1.09)
Test#2 (FP)
11.12k
19.05k (x1.71)
Test#3 (Generic, ZIP)
4.44k
4.72k (x1.06)
Test#1 (Memory)
4.64k
10.3k (x2.22)
TOTAL
31.71k
46.57k (x1.47)

Multithread

i5-3470

i5-10400T
Test#1 (Integers)
37.93k
74.58k (x1.97)
Test#2 (FP)
36.37k
126.96k (x3.49)
Test#3 (Generic, ZIP)
14.14k
31.76k (x2.25)
Test#1 (Memory)
5.71k
2.5k (x0.44)
TOTAL
94.15k
235.8k (x2.5)

Performance/W
i5-3470
i5-10400T
Test#1 (Integers)
493 points/W
2131 points/W
Test#2 (FP)
472 points/W
3627 points/W
Test#3 (Generic, ZIP)
184 points/W
907 points/W
Test#1 (Memory)
74 points/W
71 points/W
TOTAL
1223 points/W
6737 points/W

Performance/GHz
i5-3470
i5-10400T
Test#1 (Integers)
3196 points/GHz
3472 points/GHz
Test#2 (FP)
3090 points/GHz
5292 points/GHz
Test#3 (Generic, ZIP)
1234 points/GHz
1312 points/GHz
Test#1 (Memory)
1289 points/GHz
2860 points/GHz
TOTAL
8809 points/GHz
12936 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