Geekbench AI Score

727
Single Precision Score
27760
Half Precision Score
62886
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 27 2025 05:09 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
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% 469
87.1 IPS
 
Image Classification (HP)
100% 21029
3.91 KIPS
 
Image Classification (Q)
97% 49578
9.25 KIPS
 
Image Segmentation (SP)
100% 604
9.80 IPS
 
Image Segmentation (HP)
100% 13688
221.9 IPS
 
Image Segmentation (Q)
98% 42477
690.7 IPS
 
Pose Estimation (SP)
100% 780
0.91 IPS
 
Pose Estimation (HP)
100% 122832
143.3 IPS
 
Pose Estimation (Q)
98% 478684
560.3 IPS
 
Object Detection (SP)
100% 432
34.3 IPS
 
Object Detection (HP)
100% 19695
1.56 KIPS
 
Object Detection (Q)
85% 22900
1.84 KIPS
 
Face Detection (SP)
100% 1093
13.0 IPS
 
Face Detection (HP)
100% 44395
527.5 IPS
 
Face Detection (Q)
97% 164098
1.96 KIPS
 
Depth Estimation (SP)
100% 958
7.38 IPS
 
Depth Estimation (HP)
99% 84758
653.0 IPS
 
Depth Estimation (Q)
63% 147255
1.36 KIPS
 
Style Transfer (SP)
100% 1586
2.04 IPS
 
Style Transfer (HP)
98% 98848
127.5 IPS
 
Style Transfer (Q)
98% 491224
633.4 IPS
 
Image Super-Resolution (SP)
100% 388
14.3 IPS
 
Image Super-Resolution (HP)
100% 54963
2.03 KIPS
 
Image Super-Resolution (Q)
97% 135009
5.00 KIPS
 
Text Classification (SP)
100% 621
829.4 IPS
 
Text Classification (HP)
100% 3927
5.24 KIPS
 
Text Classification (Q)
93% 8065
10.8 KIPS
 
Machine Translation (SP)
100% 1083
18.7 IPS
 
Machine Translation (HP)
100% 4862
83.8 IPS
 
Machine Translation (Q)
56% 3242
83.5 IPS
 

Compare

Set Baseline Geekbench 6 now available