Geekbench AI Score

200
Single Precision Score
192
Half Precision Score
482
Quantized Score
Geekbench AI 1.7.0 for Android AArch64

Result Information

User M91
Upload Date March 21 2026 01:13 AM
Views 8

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% 169
2.74 IPS
 
Image Segmentation (Q)
98% 374
6.08 IPS
 
Pose Estimation (SP)
100% 218
0.25 IPS
 
Pose Estimation (HP)
100% 204
0.24 IPS
 
Pose Estimation (Q)
98% 848
0.99 IPS
 
Object Detection (SP)
100% 120
9.48 IPS
 
Object Detection (HP)
100% 121
9.57 IPS
 
Object Detection (Q)
87% 340
27.3 IPS
 
Face Detection (SP)
100% 313
3.72 IPS
 
Face Detection (HP)
100% 310
3.69 IPS
 
Face Detection (Q)
97% 686
8.18 IPS
 
Depth Estimation (SP)
100% 258
1.99 IPS
 
Depth Estimation (HP)
99% 239
1.84 IPS
 
Depth Estimation (Q)
64% 599
5.44 IPS
 
Style Transfer (SP)
100% 391
0.50 IPS
 
Style Transfer (HP)
100% 315
0.41 IPS
 
Style Transfer (Q)
98% 1189
1.53 IPS
 
Image Super-Resolution (SP)
100% 126
4.67 IPS
 
Image Super-Resolution (HP)
100% 122
4.51 IPS
 
Image Super-Resolution (Q)
97% 429
15.9 IPS
 
Text Classification (SP)
100% 169
225.5 IPS
 
Text Classification (HP)
100% 169
225.4 IPS
 
Text Classification (Q)
91% 332
445.9 IPS
 
Machine Translation (SP)
100% 297
5.12 IPS
 
Machine Translation (HP)
100% 289
4.97 IPS
 
Machine Translation (Q)
57% 276
6.76 IPS
 

Compare

Set Baseline Geekbench 6 now available