Geekbench AI Score

455
Single Precision Score
27353
Half Precision Score
66544
Quantized Score
Geekbench AI 1.6.1 for Android AArch64

Result Information

User Angus72
Upload Date February 02 2026 01:10 PM
Views 36

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm Snapdragon 8 Elite
System Information
Operating System Android 16
Model Samsung Galaxy S25 Ultra
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 10.85 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 363
67.6 IPS
 
Image Classification (HP)
100% 21092
3.92 KIPS
 
Image Classification (Q)
96% 50935
9.51 KIPS
 
Image Segmentation (SP)
100% 480
7.78 IPS
 
Image Segmentation (HP)
100% 13726
222.5 IPS
 
Image Segmentation (Q)
98% 52215
849.0 IPS
 
Pose Estimation (SP)
100% 624
0.73 IPS
 
Pose Estimation (HP)
100% 124053
144.7 IPS
 
Pose Estimation (Q)
98% 479364
561.1 IPS
 
Object Detection (SP)
100% 262
20.8 IPS
 
Object Detection (HP)
100% 18524
1.47 KIPS
 
Object Detection (Q)
85% 27113
2.18 KIPS
 
Face Detection (SP)
100% 567
6.74 IPS
 
Face Detection (HP)
100% 36755
436.7 IPS
 
Face Detection (Q)
97% 119642
1.43 KIPS
 
Depth Estimation (SP)
100% 478
3.69 IPS
 
Depth Estimation (HP)
99% 80270
618.4 IPS
 
Depth Estimation (Q)
63% 163510
1.52 KIPS
 
Style Transfer (SP)
100% 1096
1.41 IPS
 
Style Transfer (HP)
100% 92651
119.1 IPS
 
Style Transfer (Q)
98% 482964
622.8 IPS
 
Image Super-Resolution (SP)
100% 254
9.39 IPS
 
Image Super-Resolution (HP)
100% 52589
1.94 KIPS
 
Image Super-Resolution (Q)
97% 128405
4.76 KIPS
 
Text Classification (SP)
100% 317
422.6 IPS
 
Text Classification (HP)
100% 4392
5.86 KIPS
 
Text Classification (Q)
93% 11738
15.8 KIPS
 
Machine Translation (SP)
100% 569
9.81 IPS
 
Machine Translation (HP)
100% 5582
96.2 IPS
 
Machine Translation (Q)
56% 3459
89.1 IPS
 

Compare

Set Baseline Geekbench AI now available