Geekbench AI Score

180
Single Precision Score
179
Half Precision Score
485
Quantized Score
Geekbench AI 1.7.0 for Android AArch64

Result Information

User M91
Upload Date March 25 2026 09:36 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% 122
22.6 IPS
 
Image Classification (HP)
100% 123
22.8 IPS
 
Image Classification (Q)
99% 329
61.3 IPS
 
Image Segmentation (SP)
100% 167
2.71 IPS
 
Image Segmentation (HP)
100% 168
2.73 IPS
 
Image Segmentation (Q)
98% 374
6.08 IPS
 
Pose Estimation (SP)
100% 220
0.26 IPS
 
Pose Estimation (HP)
100% 210
0.25 IPS
 
Pose Estimation (Q)
98% 849
0.99 IPS
 
Object Detection (SP)
100% 122
9.68 IPS
 
Object Detection (HP)
100% 119
9.47 IPS
 
Object Detection (Q)
87% 345
27.6 IPS
 
Face Detection (SP)
100% 318
3.78 IPS
 
Face Detection (HP)
100% 320
3.80 IPS
 
Face Detection (Q)
97% 674
8.03 IPS
 
Depth Estimation (SP)
100% 267
2.06 IPS
 
Depth Estimation (HP)
99% 258
1.99 IPS
 
Depth Estimation (Q)
64% 648
5.88 IPS
 
Style Transfer (SP)
100% 130
0.17 IPS
 
Style Transfer (HP)
100% 131
0.17 IPS
 
Style Transfer (Q)
98% 1108
1.43 IPS
 
Image Super-Resolution (SP)
100% 122
4.49 IPS
 
Image Super-Resolution (HP)
100% 126
4.67 IPS
 
Image Super-Resolution (Q)
97% 439
16.3 IPS
 
Text Classification (SP)
100% 169
225.7 IPS
 
Text Classification (HP)
100% 170
226.8 IPS
 
Text Classification (Q)
91% 339
456.2 IPS
 
Machine Translation (SP)
100% 297
5.11 IPS
 
Machine Translation (HP)
100% 288
4.96 IPS
 
Machine Translation (Q)
57% 281
6.87 IPS
 

Compare

Set Baseline Geekbench 6 now available