Geekbench AI Score

1126
Single Precision Score
1788
Half Precision Score
1785
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User xDJoelDx
Upload Date February 27 2025 05:35 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model samsung SM-S938B
Model IDsamsung SM-S938B
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% 527
98.0 IPS
 
Image Classification (HP)
100% 729
135.6 IPS
 
Image Classification (Q)
99% 701
130.8 IPS
 
Image Segmentation (SP)
100% 1470
23.8 IPS
 
Image Segmentation (HP)
100% 1270
20.6 IPS
 
Image Segmentation (Q)
98% 1324
21.5 IPS
 
Pose Estimation (SP)
100% 1634
1.91 IPS
 
Pose Estimation (HP)
100% 1868
2.18 IPS
 
Pose Estimation (Q)
96% 2030
2.38 IPS
 
Object Detection (SP)
100% 416
33.0 IPS
 
Object Detection (HP)
100% 1047
83.1 IPS
 
Object Detection (Q)
86% 1005
80.7 IPS
 
Face Detection (SP)
100% 2441
29.0 IPS
 
Face Detection (HP)
100% 3894
46.3 IPS
 
Face Detection (Q)
97% 3928
46.8 IPS
 
Depth Estimation (SP)
100% 1472
11.3 IPS
 
Depth Estimation (HP)
99% 4046
31.3 IPS
 
Depth Estimation (Q)
63% 3320
30.9 IPS
 
Style Transfer (SP)
100% 4737
6.09 IPS
 
Style Transfer (HP)
100% 10196
13.1 IPS
 
Style Transfer (Q)
98% 10728
13.8 IPS
 
Image Super-Resolution (SP)
100% 551
20.3 IPS
 
Image Super-Resolution (HP)
100% 1698
62.7 IPS
 
Image Super-Resolution (Q)
97% 1639
60.7 IPS
 
Text Classification (SP)
100% 667
890.1 IPS
 
Text Classification (HP)
100% 674
899.1 IPS
 
Text Classification (Q)
91% 1091
1.47 KIPS
 
Machine Translation (SP)
100% 1001
17.3 IPS
 
Machine Translation (HP)
100% 1005
17.3 IPS
 
Machine Translation (Q)
57% 697
17.0 IPS
 

Compare

Set Baseline Geekbench 6 now available