Geekbench AI Score

585
Single Precision Score
26802
Half Precision Score
60901
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

Upload Date January 11 2026 04:05 PM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 16
Model samsung SM-F966B
Model IDsamsung SM-F966B
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% 443
82.4 IPS
 
Image Classification (HP)
100% 21357
3.97 KIPS
 
Image Classification (Q)
97% 49729
9.28 KIPS
 
Image Segmentation (SP)
100% 557
9.04 IPS
 
Image Segmentation (HP)
100% 13609
220.6 IPS
 
Image Segmentation (Q)
98% 41340
672.2 IPS
 
Pose Estimation (SP)
100% 568
0.66 IPS
 
Pose Estimation (HP)
100% 123342
143.9 IPS
 
Pose Estimation (Q)
98% 478674
560.3 IPS
 
Object Detection (SP)
100% 368
29.2 IPS
 
Object Detection (HP)
100% 17910
1.42 KIPS
 
Object Detection (Q)
85% 21846
1.76 KIPS
 
Face Detection (SP)
100% 754
8.96 IPS
 
Face Detection (HP)
100% 40871
485.6 IPS
 
Face Detection (Q)
97% 144158
1.72 KIPS
 
Depth Estimation (SP)
100% 702
5.41 IPS
 
Depth Estimation (HP)
99% 82800
637.9 IPS
 
Depth Estimation (Q)
63% 144096
1.33 KIPS
 
Style Transfer (SP)
100% 1158
1.49 IPS
 
Style Transfer (HP)
98% 98721
127.3 IPS
 
Style Transfer (Q)
98% 492412
635.0 IPS
 
Image Super-Resolution (SP)
100% 388
14.3 IPS
 
Image Super-Resolution (HP)
100% 53330
1.97 KIPS
 
Image Super-Resolution (Q)
97% 135146
5.01 KIPS
 
Text Classification (SP)
100% 497
663.2 IPS
 
Text Classification (HP)
100% 3906
5.21 KIPS
 
Text Classification (Q)
93% 8081
10.8 KIPS
 
Machine Translation (SP)
100% 779
13.4 IPS
 
Machine Translation (HP)
100% 4281
73.7 IPS
 
Machine Translation (Q)
56% 2923
75.3 IPS
 

Compare

Set Baseline Geekbench 6 now available