Geekbench AI Score

611
Single Precision Score
27201
Half Precision Score
61759
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date September 02 2025 06:04 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 16
Model samsung SM-F966B
Model IDsamsung SM-F966B
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% 455
84.7 IPS
 
Image Classification (HP)
100% 21458
3.99 KIPS
 
Image Classification (Q)
97% 50067
9.34 KIPS
 
Image Segmentation (SP)
100% 571
9.26 IPS
 
Image Segmentation (HP)
100% 13518
219.1 IPS
 
Image Segmentation (Q)
98% 42610
692.9 IPS
 
Pose Estimation (SP)
100% 638
0.74 IPS
 
Pose Estimation (HP)
100% 123811
144.5 IPS
 
Pose Estimation (Q)
98% 478639
560.2 IPS
 
Object Detection (SP)
100% 407
32.2 IPS
 
Object Detection (HP)
100% 18918
1.50 KIPS
 
Object Detection (Q)
85% 22359
1.80 KIPS
 
Face Detection (SP)
100% 809
9.62 IPS
 
Face Detection (HP)
100% 40956
486.6 IPS
 
Face Detection (Q)
97% 144026
1.72 KIPS
 
Depth Estimation (SP)
100% 734
5.65 IPS
 
Depth Estimation (HP)
99% 83655
644.5 IPS
 
Depth Estimation (Q)
63% 145132
1.34 KIPS
 
Style Transfer (SP)
100% 1164
1.50 IPS
 
Style Transfer (HP)
98% 98767
127.4 IPS
 
Style Transfer (Q)
98% 492130
634.6 IPS
 
Image Super-Resolution (SP)
100% 388
14.3 IPS
 
Image Super-Resolution (HP)
100% 53414
1.97 KIPS
 
Image Super-Resolution (Q)
97% 135494
5.02 KIPS
 
Text Classification (SP)
100% 525
701.3 IPS
 
Text Classification (HP)
100% 3918
5.23 KIPS
 
Text Classification (Q)
93% 8157
10.9 KIPS
 
Machine Translation (SP)
100% 776
13.4 IPS
 
Machine Translation (HP)
100% 4609
79.4 IPS
 
Machine Translation (Q)
56% 3110
80.1 IPS
 

Compare

Set Baseline Geekbench 6 now available