Geekbench AI Score

531
Single Precision Score
26649
Half Precision Score
60288
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

Upload Date November 05 2025 10:12 AM
Views 8

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 16
Model samsung SM-F966N
Model IDsamsung SM-F966N
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% 446
82.9 IPS
 
Image Classification (HP)
100% 21293
3.96 KIPS
 
Image Classification (Q)
97% 49806
9.29 KIPS
 
Image Segmentation (SP)
100% 562
9.12 IPS
 
Image Segmentation (HP)
100% 13527
219.3 IPS
 
Image Segmentation (Q)
98% 40313
655.5 IPS
 
Pose Estimation (SP)
100% 539
0.63 IPS
 
Pose Estimation (HP)
100% 123156
143.7 IPS
 
Pose Estimation (Q)
98% 477862
559.3 IPS
 
Object Detection (SP)
100% 341
27.1 IPS
 
Object Detection (HP)
100% 18004
1.43 KIPS
 
Object Detection (Q)
85% 21659
1.74 KIPS
 
Face Detection (SP)
100% 679
8.07 IPS
 
Face Detection (HP)
100% 40048
475.9 IPS
 
Face Detection (Q)
97% 136489
1.63 KIPS
 
Depth Estimation (SP)
100% 627
4.83 IPS
 
Depth Estimation (HP)
99% 81648
629.0 IPS
 
Depth Estimation (Q)
63% 142430
1.32 KIPS
 
Style Transfer (SP)
100% 974
1.25 IPS
 
Style Transfer (HP)
98% 98290
126.7 IPS
 
Style Transfer (Q)
98% 490234
632.2 IPS
 
Image Super-Resolution (SP)
100% 305
11.3 IPS
 
Image Super-Resolution (HP)
100% 53255
1.97 KIPS
 
Image Super-Resolution (Q)
97% 134934
5.00 KIPS
 
Text Classification (SP)
100% 497
663.0 IPS
 
Text Classification (HP)
100% 3877
5.18 KIPS
 
Text Classification (Q)
93% 8041
10.8 KIPS
 
Machine Translation (SP)
100% 626
10.8 IPS
 
Machine Translation (HP)
100% 4264
73.5 IPS
 
Machine Translation (Q)
56% 2952
76.1 IPS
 

Compare

Set Baseline Geekbench 6 now available