Geekbench AI Score

729
Single Precision Score
635
Half Precision Score
1122
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date May 08 2025 01:45 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 888
System Information
Operating System Android 15
Model Samsung Galaxy Z Fold3 5G
Model IDsamsung SM-F926B
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM SM8350
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 11.09 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 501
93.1 IPS
 
Image Classification (HP)
100% 509
94.7 IPS
 
Image Classification (Q)
100% 1454
270.3 IPS
 
Image Segmentation (SP)
100% 587
9.51 IPS
 
Image Segmentation (HP)
100% 579
9.38 IPS
 
Image Segmentation (Q)
98% 1638
26.6 IPS
 
Pose Estimation (SP)
100% 2103
2.45 IPS
 
Pose Estimation (HP)
100% 1843
2.15 IPS
 
Pose Estimation (Q)
84% 2282
2.71 IPS
 
Object Detection (SP)
100% 343
27.2 IPS
 
Object Detection (HP)
100% 345
27.4 IPS
 
Object Detection (Q)
83% 820
66.2 IPS
 
Face Detection (SP)
100% 1181
14.0 IPS
 
Face Detection (HP)
100% 1144
13.6 IPS
 
Face Detection (Q)
95% 2275
27.2 IPS
 
Depth Estimation (SP)
100% 1609
12.4 IPS
 
Depth Estimation (HP)
99% 1533
11.8 IPS
 
Depth Estimation (Q)
64% 2169
19.9 IPS
 
Style Transfer (SP)
89% 2825
3.67 IPS
 
Style Transfer (HP)
89% 2720
3.53 IPS
 
Style Transfer (Q)
98% 5422
6.99 IPS
 
Image Super-Resolution (SP)
100% 857
31.6 IPS
 
Image Super-Resolution (HP)
100% 289
10.7 IPS
 
Image Super-Resolution (Q)
97% 642
23.8 IPS
 
Text Classification (SP)
100% 173
230.5 IPS
 
Text Classification (HP)
100% 171
228.4 IPS
 
Text Classification (Q)
88% 275
370.2 IPS
 
Machine Translation (SP)
100% 254
4.37 IPS
 
Machine Translation (HP)
100% 243
4.18 IPS
 
Machine Translation (Q)
50% 151
5.36 IPS
 

Compare

Set Baseline Geekbench 6 now available
OSZAR »