Geekbench AI Score

38
Single Precision Score
54
Half Precision Score
51
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 04 2024 06:47 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 14
Model NUU S6601L
Model IDNUU S6601L
Motherboard k65v1_64_bsp_k510
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 2.20 GHz
Cluster 14 Cores @ 1.60 GHz
Cluster 24 Cores @ 2.20 GHz
Memory Information
Size 5.67 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 25
4.58 IPS
 
Image Classification (HP)
100% 37
6.84 IPS
 
Image Classification (Q)
99% 36
6.63 IPS
 
Image Segmentation (SP)
100% 39
0.63 IPS
 
Image Segmentation (HP)
100% 48
0.77 IPS
 
Image Segmentation (Q)
98% 47
0.77 IPS
 
Pose Estimation (SP)
100% 30
0.04 IPS
 
Pose Estimation (HP)
100% 52
0.06 IPS
 
Pose Estimation (Q)
95% 48
0.06 IPS
 
Object Detection (SP)
100% 18
1.43 IPS
 
Object Detection (HP)
100% 26
2.08 IPS
 
Object Detection (Q)
85% 25
2.03 IPS
 
Face Detection (SP)
100% 75
0.89 IPS
 
Face Detection (HP)
100% 100
1.19 IPS
 
Face Detection (Q)
97% 94
1.12 IPS
 
Depth Estimation (SP)
100% 48
0.37 IPS
 
Depth Estimation (HP)
99% 75
0.58 IPS
 
Depth Estimation (Q)
63% 59
0.55 IPS
 
Style Transfer (SP)
100% 96
0.12 IPS
 
Style Transfer (HP)
100% 162
0.21 IPS
 
Style Transfer (Q)
98% 153
0.20 IPS
 
Image Super-Resolution (SP)
100% 21
0.78 IPS
 
Image Super-Resolution (HP)
100% 36
1.32 IPS
 
Image Super-Resolution (Q)
97% 33
1.21 IPS
 
Text Classification (SP)
100% 34
45.6 IPS
 
Text Classification (HP)
100% 34
45.4 IPS
 
Text Classification (Q)
91% 49
65.5 IPS
 
Machine Translation (SP)
100% 61
1.05 IPS
 
Machine Translation (HP)
100% 60
1.03 IPS
 
Machine Translation (Q)
57% 46
1.12 IPS
 

Compare

Set Baseline Geekbench 6 now available