Geekbench AI Score

171
Single Precision Score
168
Half Precision Score
456
Quantized Score
Geekbench AI 1.7.0 for Android AArch64

Result Information

User M91
Upload Date April 12 2026 09:49 AM
Views 5

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM ARMv8
System Information
Operating System Android 16
Model samsung SM-A166W
Model IDsamsung SM-A166W
Motherboard s5e8535
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 3.37 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 119
22.2 IPS
 
Image Classification (HP)
100% 122
22.6 IPS
 
Image Classification (Q)
99% 329
61.3 IPS
 
Image Segmentation (SP)
100% 168
2.72 IPS
 
Image Segmentation (HP)
100% 168
2.73 IPS
 
Image Segmentation (Q)
98% 374
6.08 IPS
 
Pose Estimation (SP)
100% 219
0.26 IPS
 
Pose Estimation (HP)
100% 201
0.23 IPS
 
Pose Estimation (Q)
98% 832
0.97 IPS
 
Object Detection (SP)
100% 120
9.54 IPS
 
Object Detection (HP)
100% 117
9.29 IPS
 
Object Detection (Q)
87% 328
26.3 IPS
 
Face Detection (SP)
100% 307
3.64 IPS
 
Face Detection (HP)
100% 302
3.59 IPS
 
Face Detection (Q)
97% 665
7.93 IPS
 
Depth Estimation (SP)
100% 254
1.95 IPS
 
Depth Estimation (HP)
99% 245
1.89 IPS
 
Depth Estimation (Q)
64% 598
5.43 IPS
 
Style Transfer (SP)
100% 130
0.17 IPS
 
Style Transfer (HP)
100% 114
0.15 IPS
 
Style Transfer (Q)
98% 1040
1.34 IPS
 
Image Super-Resolution (SP)
100% 104
3.83 IPS
 
Image Super-Resolution (HP)
100% 111
4.10 IPS
 
Image Super-Resolution (Q)
97% 381
14.1 IPS
 
Text Classification (SP)
100% 145
193.8 IPS
 
Text Classification (HP)
100% 151
201.5 IPS
 
Text Classification (Q)
91% 285
382.5 IPS
 
Machine Translation (SP)
100% 269
4.64 IPS
 
Machine Translation (HP)
100% 271
4.66 IPS
 
Machine Translation (Q)
57% 262
6.41 IPS
 

Compare

Set Baseline Geekbench 6 now available