Geekbench AI Score

499
Single Precision Score
26991
Half Precision Score
60082
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date August 04 2025 01:30 AM
Views 9

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 16
Model samsung SM-F966U
Model IDsamsung SM-F966U
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 10.83 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 457
85.0 IPS
 
Image Classification (HP)
100% 21431
3.99 KIPS
 
Image Classification (Q)
97% 50433
9.41 KIPS
 
Image Segmentation (SP)
100% 576
9.34 IPS
 
Image Segmentation (HP)
100% 13723
222.5 IPS
 
Image Segmentation (Q)
98% 42460
690.4 IPS
 
Pose Estimation (SP)
100% 507
0.59 IPS
 
Pose Estimation (HP)
100% 123462
144.1 IPS
 
Pose Estimation (Q)
98% 474510
555.4 IPS
 
Object Detection (SP)
100% 253
20.1 IPS
 
Object Detection (HP)
100% 18751
1.49 KIPS
 
Object Detection (Q)
85% 21478
1.73 KIPS
 
Face Detection (SP)
100% 665
7.90 IPS
 
Face Detection (HP)
100% 40268
478.5 IPS
 
Face Detection (Q)
97% 132254
1.58 KIPS
 
Depth Estimation (SP)
100% 619
4.77 IPS
 
Depth Estimation (HP)
99% 83149
640.6 IPS
 
Depth Estimation (Q)
63% 137037
1.27 KIPS
 
Style Transfer (SP)
100% 1020
1.31 IPS
 
Style Transfer (HP)
98% 98184
126.6 IPS
 
Style Transfer (Q)
98% 489424
631.1 IPS
 
Image Super-Resolution (SP)
100% 317
11.7 IPS
 
Image Super-Resolution (HP)
100% 52882
1.95 KIPS
 
Image Super-Resolution (Q)
97% 134731
4.99 KIPS
 
Text Classification (SP)
100% 315
419.8 IPS
 
Text Classification (HP)
100% 3876
5.17 KIPS
 
Text Classification (Q)
93% 8016
10.8 KIPS
 
Machine Translation (SP)
100% 687
11.8 IPS
 
Machine Translation (HP)
100% 4473
77.1 IPS
 
Machine Translation (Q)
56% 2932
75.5 IPS
 

Compare

Set Baseline Geekbench 6 now available