Geekbench AI Score

698
Single Precision Score
31317
Half Precision Score
80146
Quantized Score
Geekbench AI 1.7.0 for Android AArch64

Result Information

User kristofersodersten
Upload Date August 07 2026 01:27 PM
Views 12

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 16
Model samsung SM-S948B
Model IDsamsung SM-S948B
Motherboard canoe
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 2 revision 1
Base Frequency 3.63 GHz
Cluster 16 Cores @ 3.63 GHz
Cluster 22 Cores @ 4.74 GHz
Memory Information
Size 10.86 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 499
92.7 IPS
 
Image Classification (HP)
100% 24935
4.64 KIPS
 
Image Classification (Q)
96% 48341
9.03 KIPS
 
Image Segmentation (SP)
100% 627
10.2 IPS
 
Image Segmentation (HP)
100% 16271
263.8 IPS
 
Image Segmentation (Q)
98% 64091
1.04 KIPS
 
Pose Estimation (SP)
100% 789
0.92 IPS
 
Pose Estimation (HP)
100% 153850
179.5 IPS
 
Pose Estimation (Q)
98% 633347
741.3 IPS
 
Object Detection (SP)
100% 416
33.0 IPS
 
Object Detection (HP)
100% 24419
1.94 KIPS
 
Object Detection (Q)
85% 32981
2.65 KIPS
 
Face Detection (SP)
100% 1119
13.3 IPS
 
Face Detection (HP)
100% 48169
572.4 IPS
 
Face Detection (Q)
97% 173045
2.06 KIPS
 
Depth Estimation (SP)
100% 937
7.22 IPS
 
Depth Estimation (HP)
99% 85431
658.2 IPS
 
Depth Estimation (Q)
63% 197496
1.84 KIPS
 
Style Transfer (SP)
100% 1341
1.72 IPS
 
Style Transfer (HP)
100% 98025
126.0 IPS
 
Style Transfer (Q)
98% 593773
765.7 IPS
 
Image Super-Resolution (SP)
100% 414
15.3 IPS
 
Image Super-Resolution (HP)
100% 57176
2.11 KIPS
 
Image Super-Resolution (Q)
97% 167321
6.20 KIPS
 
Text Classification (SP)
100% 519
692.6 IPS
 
Text Classification (HP)
100% 4267
5.69 KIPS
 
Text Classification (Q)
93% 10807
14.5 KIPS
 
Machine Translation (SP)
100% 889
15.3 IPS
 
Machine Translation (HP)
100% 6051
104.2 IPS
 
Machine Translation (Q)
56% 4605
118.6 IPS
 

Compare

Set Baseline Geekbench AI now available