Geekbench AI Score

531
Single Precision Score
27016
Half Precision Score
60227
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date July 10 2025 09:55 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
85.1 IPS
 
Image Classification (HP)
100% 21444
3.99 KIPS
 
Image Classification (Q)
97% 49906
9.31 KIPS
 
Image Segmentation (SP)
100% 580
9.40 IPS
 
Image Segmentation (HP)
100% 13646
221.2 IPS
 
Image Segmentation (Q)
98% 41660
677.4 IPS
 
Pose Estimation (SP)
100% 668
0.78 IPS
 
Pose Estimation (HP)
100% 123365
143.9 IPS
 
Pose Estimation (Q)
98% 477644
559.1 IPS
 
Object Detection (SP)
100% 268
21.3 IPS
 
Object Detection (HP)
100% 18919
1.50 KIPS
 
Object Detection (Q)
85% 22023
1.77 KIPS
 
Face Detection (SP)
100% 771
9.16 IPS
 
Face Detection (HP)
100% 40978
486.9 IPS
 
Face Detection (Q)
97% 136097
1.62 KIPS
 
Depth Estimation (SP)
100% 661
5.10 IPS
 
Depth Estimation (HP)
99% 82853
638.3 IPS
 
Depth Estimation (Q)
63% 141575
1.31 KIPS
 
Style Transfer (SP)
100% 1078
1.39 IPS
 
Style Transfer (HP)
98% 98444
126.9 IPS
 
Style Transfer (Q)
98% 489382
631.1 IPS
 
Image Super-Resolution (SP)
100% 315
11.6 IPS
 
Image Super-Resolution (HP)
100% 52956
1.96 KIPS
 
Image Super-Resolution (Q)
97% 132363
4.90 KIPS
 
Text Classification (SP)
100% 318
423.9 IPS
 
Text Classification (HP)
100% 3865
5.16 KIPS
 
Text Classification (Q)
93% 7890
10.6 KIPS
 
Machine Translation (SP)
100% 682
11.7 IPS
 
Machine Translation (HP)
100% 4434
76.4 IPS
 
Machine Translation (Q)
56% 2916
75.1 IPS
 

Compare

Set Baseline Geekbench 6 now available