Geekbench AI Score

271
Single Precision Score
261
Half Precision Score
270
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 28 2024 10:42 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model samsung SM-G525N
Model IDsamsung SM-G525N
Motherboard exynos850
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3333 revision 1
Base Frequency 2.00 GHz
Cluster 18 Cores @ 2.00 GHz
Memory Information
Size 3.57 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 132
24.6 IPS
 
Image Classification (HP)
100% 117
21.8 IPS
 
Image Classification (Q)
100% 172
31.9 IPS
 
Image Segmentation (SP)
100% 166
2.69 IPS
 
Image Segmentation (HP)
100% 175
2.84 IPS
 
Image Segmentation (Q)
98% 261
4.24 IPS
 
Pose Estimation (SP)
100% 632
0.74 IPS
 
Pose Estimation (HP)
100% 587
0.69 IPS
 
Pose Estimation (Q)
84% 438
0.52 IPS
 
Object Detection (SP)
100% 137
10.8 IPS
 
Object Detection (HP)
100% 133
10.6 IPS
 
Object Detection (Q)
83% 171
13.8 IPS
 
Face Detection (SP)
100% 363
4.32 IPS
 
Face Detection (HP)
100% 334
3.97 IPS
 
Face Detection (Q)
95% 452
5.39 IPS
 
Depth Estimation (SP)
100% 438
3.38 IPS
 
Depth Estimation (HP)
99% 384
2.96 IPS
 
Depth Estimation (Q)
64% 435
3.98 IPS
 
Style Transfer (SP)
89% 1299
1.69 IPS
 
Style Transfer (HP)
89% 1311
1.70 IPS
 
Style Transfer (Q)
98% 1224
1.58 IPS
 
Image Super-Resolution (SP)
100% 246
9.07 IPS
 
Image Super-Resolution (HP)
100% 246
9.07 IPS
 
Image Super-Resolution (Q)
97% 251
9.31 IPS
 
Text Classification (SP)
100% 119
158.4 IPS
 
Text Classification (HP)
100% 118
157.3 IPS
 
Text Classification (Q)
88% 129
173.8 IPS
 
Machine Translation (SP)
100% 192
3.32 IPS
 
Machine Translation (HP)
100% 189
3.26 IPS
 
Machine Translation (Q)
50% 79
2.79 IPS
 

Compare

Set Baseline Geekbench 6 now available