Geekbench AI Score

597
Single Precision Score
25798
Half Precision Score
58037
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date August 04 2025 03:43 PM
Views 25

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 16
Model samsung SM-F966U1
Model IDsamsung SM-F966U1
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% 437
81.2 IPS
 
Image Classification (HP)
100% 21128
3.93 KIPS
 
Image Classification (Q)
97% 49048
9.15 KIPS
 
Image Segmentation (SP)
100% 524
8.50 IPS
 
Image Segmentation (HP)
100% 13563
219.9 IPS
 
Image Segmentation (Q)
98% 41709
678.2 IPS
 
Pose Estimation (SP)
100% 608
0.71 IPS
 
Pose Estimation (HP)
100% 111087
129.6 IPS
 
Pose Estimation (Q)
98% 433112
506.9 IPS
 
Object Detection (SP)
100% 342
27.1 IPS
 
Object Detection (HP)
100% 18035
1.43 KIPS
 
Object Detection (Q)
85% 20969
1.69 KIPS
 
Face Detection (SP)
100% 937
11.1 IPS
 
Face Detection (HP)
100% 38872
461.9 IPS
 
Face Detection (Q)
97% 136068
1.62 KIPS
 
Depth Estimation (SP)
100% 765
5.90 IPS
 
Depth Estimation (HP)
99% 76165
586.8 IPS
 
Depth Estimation (Q)
63% 134016
1.24 KIPS
 
Style Transfer (SP)
100% 1158
1.49 IPS
 
Style Transfer (HP)
98% 91058
117.4 IPS
 
Style Transfer (Q)
98% 452911
584.0 IPS
 
Image Super-Resolution (SP)
100% 398
14.7 IPS
 
Image Super-Resolution (HP)
100% 51764
1.91 KIPS
 
Image Super-Resolution (Q)
97% 128881
4.78 KIPS
 
Text Classification (SP)
100% 429
572.4 IPS
 
Text Classification (HP)
100% 3717
4.96 KIPS
 
Text Classification (Q)
93% 7626
10.2 KIPS
 
Machine Translation (SP)
100% 860
14.8 IPS
 
Machine Translation (HP)
100% 4386
75.5 IPS
 
Machine Translation (Q)
56% 2875
74.1 IPS
 

Compare

Set Baseline Geekbench 6 now available