Geekbench AI Score

514
Single Precision Score
26605
Half Precision Score
60435
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date August 29 2025 09:39 PM
Views 2

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% 454
84.5 IPS
 
Image Classification (HP)
100% 21166
3.94 KIPS
 
Image Classification (Q)
97% 50125
9.35 KIPS
 
Image Segmentation (SP)
100% 554
8.98 IPS
 
Image Segmentation (HP)
100% 13718
222.4 IPS
 
Image Segmentation (Q)
98% 41249
670.7 IPS
 
Pose Estimation (SP)
100% 516
0.60 IPS
 
Pose Estimation (HP)
100% 123647
144.3 IPS
 
Pose Estimation (Q)
98% 479739
561.5 IPS
 
Object Detection (SP)
100% 359
28.5 IPS
 
Object Detection (HP)
100% 17971
1.43 KIPS
 
Object Detection (Q)
85% 21480
1.73 KIPS
 
Face Detection (SP)
100% 640
7.61 IPS
 
Face Detection (HP)
100% 38617
458.9 IPS
 
Face Detection (Q)
97% 137026
1.63 KIPS
 
Depth Estimation (SP)
100% 568
4.38 IPS
 
Depth Estimation (HP)
99% 83334
642.0 IPS
 
Depth Estimation (Q)
63% 143418
1.33 KIPS
 
Style Transfer (SP)
100% 914
1.18 IPS
 
Style Transfer (HP)
98% 98411
126.9 IPS
 
Style Transfer (Q)
98% 492005
634.4 IPS
 
Image Super-Resolution (SP)
100% 307
11.3 IPS
 
Image Super-Resolution (HP)
100% 52784
1.95 KIPS
 
Image Super-Resolution (Q)
97% 135504
5.02 KIPS
 
Text Classification (SP)
100% 498
664.1 IPS
 
Text Classification (HP)
100% 3898
5.20 KIPS
 
Text Classification (Q)
93% 7934
10.6 KIPS
 
Machine Translation (SP)
100% 550
9.48 IPS
 
Machine Translation (HP)
100% 4227
72.8 IPS
 
Machine Translation (Q)
56% 2935
75.6 IPS
 

Compare

Set Baseline Geekbench 6 now available