Geekbench AI Score

571
Single Precision Score
25378
Half Precision Score
57768
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date August 29 2025 11:57 PM
Views 2

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% 361
67.1 IPS
 
Image Classification (HP)
100% 19127
3.56 KIPS
 
Image Classification (Q)
97% 47878
8.93 KIPS
 
Image Segmentation (SP)
100% 421
6.82 IPS
 
Image Segmentation (HP)
100% 12800
207.5 IPS
 
Image Segmentation (Q)
98% 39130
636.3 IPS
 
Pose Estimation (SP)
100% 583
0.68 IPS
 
Pose Estimation (HP)
100% 111063
129.6 IPS
 
Pose Estimation (Q)
98% 433096
506.9 IPS
 
Object Detection (SP)
100% 310
24.6 IPS
 
Object Detection (HP)
100% 18172
1.44 KIPS
 
Object Detection (Q)
85% 20987
1.69 KIPS
 
Face Detection (SP)
100% 896
10.6 IPS
 
Face Detection (HP)
100% 39444
468.7 IPS
 
Face Detection (Q)
97% 138274
1.65 KIPS
 
Depth Estimation (SP)
100% 769
5.93 IPS
 
Depth Estimation (HP)
99% 73764
568.3 IPS
 
Depth Estimation (Q)
63% 137075
1.27 KIPS
 
Style Transfer (SP)
100% 1269
1.63 IPS
 
Style Transfer (HP)
98% 91127
117.5 IPS
 
Style Transfer (Q)
98% 453337
584.6 IPS
 
Image Super-Resolution (SP)
100% 403
14.9 IPS
 
Image Super-Resolution (HP)
100% 51789
1.91 KIPS
 
Image Super-Resolution (Q)
97% 128717
4.77 KIPS
 
Text Classification (SP)
100% 429
572.3 IPS
 
Text Classification (HP)
100% 3731
4.98 KIPS
 
Text Classification (Q)
93% 7644
10.3 KIPS
 
Machine Translation (SP)
100% 895
15.4 IPS
 
Machine Translation (HP)
100% 4379
75.4 IPS
 
Machine Translation (Q)
56% 2875
74.1 IPS
 

Compare

Set Baseline Geekbench 6 now available