Geekbench AI Score

1259
Single Precision Score
2021
Half Precision Score
1900
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User dlwlrma
Upload Date February 25 2025 12:59 PM
Views 6

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model samsung SM-S938N
Model IDsamsung SM-S938N
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 1 revision 4
Base Frequency 3.53 GHz
Cluster 16 Cores @ 3.53 GHz
Cluster 22 Cores @ 4.47 GHz
Memory Information
Size 10.86 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 722
134.3 IPS
 
Image Classification (HP)
100% 728
135.4 IPS
 
Image Classification (Q)
99% 781
145.7 IPS
 
Image Segmentation (SP)
100% 1401
22.7 IPS
 
Image Segmentation (HP)
100% 1538
24.9 IPS
 
Image Segmentation (Q)
98% 1178
19.1 IPS
 
Pose Estimation (SP)
100% 1697
1.98 IPS
 
Pose Estimation (HP)
100% 2964
3.46 IPS
 
Pose Estimation (Q)
96% 2482
2.91 IPS
 
Object Detection (SP)
100% 497
39.4 IPS
 
Object Detection (HP)
100% 1168
92.7 IPS
 
Object Detection (Q)
86% 1151
92.4 IPS
 
Face Detection (SP)
100% 2877
34.2 IPS
 
Face Detection (HP)
100% 3583
42.6 IPS
 
Face Detection (Q)
97% 3774
45.0 IPS
 
Depth Estimation (SP)
100% 1601
12.3 IPS
 
Depth Estimation (HP)
99% 4911
37.9 IPS
 
Depth Estimation (Q)
63% 3760
35.0 IPS
 
Style Transfer (SP)
100% 5920
7.61 IPS
 
Style Transfer (HP)
100% 12594
16.2 IPS
 
Style Transfer (Q)
98% 10876
14.0 IPS
 
Image Super-Resolution (SP)
100% 618
22.8 IPS
 
Image Super-Resolution (HP)
100% 1931
71.3 IPS
 
Image Super-Resolution (Q)
97% 2008
74.4 IPS
 
Text Classification (SP)
100% 679
906.9 IPS
 
Text Classification (HP)
100% 677
903.6 IPS
 
Text Classification (Q)
91% 1102
1.48 KIPS
 
Machine Translation (SP)
100% 1028
17.7 IPS
 
Machine Translation (HP)
100% 1013
17.4 IPS
 
Machine Translation (Q)
57% 684
16.7 IPS
 

Compare

Set Baseline Geekbench 6 now available