Geekbench AI Score

170
Single Precision Score
169
Half Precision Score
453
Quantized Score
Geekbench AI 1.7.0 for Android AArch64

Result Information

User M91
Upload Date April 01 2026 10:33 AM
Views 9

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% 122
22.6 IPS
 
Image Classification (HP)
100% 122
22.7 IPS
 
Image Classification (Q)
99% 328
61.2 IPS
 
Image Segmentation (SP)
100% 168
2.72 IPS
 
Image Segmentation (HP)
100% 168
2.72 IPS
 
Image Segmentation (Q)
98% 373
6.07 IPS
 
Pose Estimation (SP)
100% 212
0.25 IPS
 
Pose Estimation (HP)
100% 187
0.22 IPS
 
Pose Estimation (Q)
98% 700
0.82 IPS
 
Object Detection (SP)
100% 106
8.40 IPS
 
Object Detection (HP)
100% 106
8.42 IPS
 
Object Detection (Q)
87% 300
24.1 IPS
 
Face Detection (SP)
100% 289
3.44 IPS
 
Face Detection (HP)
100% 283
3.36 IPS
 
Face Detection (Q)
97% 591
7.05 IPS
 
Depth Estimation (SP)
100% 239
1.84 IPS
 
Depth Estimation (HP)
99% 231
1.78 IPS
 
Depth Estimation (Q)
64% 537
4.87 IPS
 
Style Transfer (SP)
100% 108
0.14 IPS
 
Style Transfer (HP)
100% 121
0.15 IPS
 
Style Transfer (Q)
98% 1153
1.49 IPS
 
Image Super-Resolution (SP)
100% 123
4.54 IPS
 
Image Super-Resolution (HP)
100% 128
4.71 IPS
 
Image Super-Resolution (Q)
97% 434
16.1 IPS
 
Text Classification (SP)
100% 164
218.4 IPS
 
Text Classification (HP)
100% 172
230.2 IPS
 
Text Classification (Q)
91% 332
445.9 IPS
 
Machine Translation (SP)
100% 294
5.06 IPS
 
Machine Translation (HP)
100% 284
4.90 IPS
 
Machine Translation (Q)
57% 270
6.60 IPS
 

Compare

Set Baseline Geekbench 6 now available