Geekbench ML Score

111
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date February 04 2025 08:15 AM
Views 4

System Information

System Information
Operating System Android 14
Model nxp EVK_95
Model IDnxp EVK_95
Motherboard EVK_95
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 6 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3333 revision 0
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Memory Information
Size 14.72 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 76
8.18 IPS
 
Image Classification (F16)
100% 77
8.23 IPS
 
Image Classification (I8)
81% 256
27.4 IPS
 
Image Segmentation (F32)
100% 130
0.80 IPS
 
Image Segmentation (F16)
100% 130
0.80 IPS
 
Image Segmentation (I8)
89% 456
2.81 IPS
 
Pose Estimation (F32)
100% 66
0.27 IPS
 
Pose Estimation (F16)
100% 66
0.27 IPS
 
Pose Estimation (I8)
80% 99
0.40 IPS
 
Object Detection (F32)
100% 119
4.18 IPS
 
Object Detection (F16)
100% 118
4.15 IPS
 
Object Detection (I8)
52% 324
11.4 IPS
 
Face Detection (F32)
100% 161
1.85 IPS
 
Face Detection (F16)
100% 161
1.85 IPS
 
Face Detection (I8)
75% 389
4.47 IPS
 
Text Classification (F32)
100% 99
39.2 IPS
 
Text Classification (F16)
100% 99
39.3 IPS
 
Machine Translation (F32)
100% 19
2.97 IPS
 
Machine Translation (F16)
100% 19
2.97 IPS
 

Compare

Set Baseline Geekbench 6 now available