Geekbench AI Score

617
Single Precision Score
27251
Half Precision Score
60813
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

Upload Date September 13 2025 11:31 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model samsung SM-S931Z
Model IDsamsung SM-S931Z
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% 428
79.6 IPS
 
Image Classification (HP)
100% 21288
3.96 KIPS
 
Image Classification (Q)
97% 49225
9.19 KIPS
 
Image Segmentation (SP)
100% 531
8.61 IPS
 
Image Segmentation (HP)
100% 13711
222.3 IPS
 
Image Segmentation (Q)
98% 39859
648.1 IPS
 
Pose Estimation (SP)
100% 603
0.70 IPS
 
Pose Estimation (HP)
100% 120819
141.0 IPS
 
Pose Estimation (Q)
98% 478326
559.9 IPS
 
Object Detection (SP)
100% 363
28.8 IPS
 
Object Detection (HP)
100% 18294
1.45 KIPS
 
Object Detection (Q)
85% 21141
1.70 KIPS
 
Face Detection (SP)
100% 886
10.5 IPS
 
Face Detection (HP)
100% 42328
502.9 IPS
 
Face Detection (Q)
97% 145622
1.74 KIPS
 
Depth Estimation (SP)
100% 775
5.97 IPS
 
Depth Estimation (HP)
99% 83942
646.7 IPS
 
Depth Estimation (Q)
63% 144355
1.34 KIPS
 
Style Transfer (SP)
100% 1329
1.71 IPS
 
Style Transfer (HP)
98% 98763
127.4 IPS
 
Style Transfer (Q)
98% 491613
633.9 IPS
 
Image Super-Resolution (SP)
100% 431
15.9 IPS
 
Image Super-Resolution (HP)
100% 54031
2.00 KIPS
 
Image Super-Resolution (Q)
97% 134888
5.00 KIPS
 
Text Classification (SP)
100% 459
612.8 IPS
 
Text Classification (HP)
100% 3901
5.21 KIPS
 
Text Classification (Q)
93% 7941
10.7 KIPS
 
Machine Translation (SP)
100% 897
15.5 IPS
 
Machine Translation (HP)
100% 4734
81.6 IPS
 
Machine Translation (Q)
56% 3150
81.2 IPS
 

Compare

Set Baseline Geekbench 6 now available