Geekbench ML Score

287
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 24 2022 06:17 PM
Views 2

System Information

System Information
Operating System Android 12
Model Samsung Galaxy Note20 Ultra
Model IDsamsung SM-N986B
Motherboard exynos990
Governorenergy_step
CPU Information
Name ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 83 architecture 8 variant 1 part 4 revision 0
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.50 GHz
Cluster 32 Cores @ 2.73 GHz
Memory Information
Size 10.64 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 190
20.4 IPS
 
Image Classification (F16)
100% 188
20.1 IPS
 
Image Classification (I8)
81% 171
18.3 IPS
 
Image Segmentation (F32)
100% 445
2.75 IPS
 
Image Segmentation (F16)
100% 410
2.53 IPS
 
Image Segmentation (I8)
89% 673
4.15 IPS
 
Pose Estimation (F32)
100% 216
0.87 IPS
 
Pose Estimation (F16)
100% 214
0.86 IPS
 
Pose Estimation (I8)
80% 193
0.78 IPS
 
Object Detection (F32)
100% 235
8.24 IPS
 
Object Detection (F16)
100% 236
8.26 IPS
 
Object Detection (I8)
52% 212
7.45 IPS
 
Face Detection (F32)
100% 421
4.84 IPS
 
Face Detection (F16)
100% 419
4.82 IPS
 
Face Detection (I8)
75% 415
4.77 IPS
 
Text Classification (F32)
100% 243
96.2 IPS
 
Text Classification (F16)
100% 247
97.5 IPS
 
Machine Translation (F32)
100% 397
61.1 IPS
 
Machine Translation (F16)
100% 388
59.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download