Geekbench AI Score

523
Single Precision Score
27024
Half Precision Score
60271
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date July 10 2025 06:21 AM
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% 458
85.2 IPS
 
Image Classification (HP)
100% 21327
3.97 KIPS
 
Image Classification (Q)
97% 49921
9.32 KIPS
 
Image Segmentation (SP)
100% 581
9.42 IPS
 
Image Segmentation (HP)
100% 13637
221.1 IPS
 
Image Segmentation (Q)
98% 42534
691.6 IPS
 
Pose Estimation (SP)
100% 603
0.70 IPS
 
Pose Estimation (HP)
100% 123255
143.8 IPS
 
Pose Estimation (Q)
98% 476756
558.0 IPS
 
Object Detection (SP)
100% 271
21.5 IPS
 
Object Detection (HP)
100% 18871
1.50 KIPS
 
Object Detection (Q)
85% 21870
1.76 KIPS
 
Face Detection (SP)
100% 768
9.12 IPS
 
Face Detection (HP)
100% 40956
486.6 IPS
 
Face Detection (Q)
97% 135696
1.62 KIPS
 
Depth Estimation (SP)
100% 649
5.00 IPS
 
Depth Estimation (HP)
99% 83015
639.6 IPS
 
Depth Estimation (Q)
63% 141631
1.31 KIPS
 
Style Transfer (SP)
100% 1051
1.35 IPS
 
Style Transfer (HP)
98% 98415
126.9 IPS
 
Style Transfer (Q)
98% 489191
630.8 IPS
 
Image Super-Resolution (SP)
100% 314
11.6 IPS
 
Image Super-Resolution (HP)
100% 52831
1.95 KIPS
 
Image Super-Resolution (Q)
97% 130684
4.84 KIPS
 
Text Classification (SP)
100% 317
422.9 IPS
 
Text Classification (HP)
100% 3892
5.20 KIPS
 
Text Classification (Q)
93% 7986
10.7 KIPS
 
Machine Translation (SP)
100% 681
11.7 IPS
 
Machine Translation (HP)
100% 4464
76.9 IPS
 
Machine Translation (Q)
56% 2912
75.0 IPS
 

Compare

Set Baseline Geekbench 6 now available