Geekbench AI Score

414
Single Precision Score
24388
Half Precision Score
55498
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

Upload Date September 21 2025 02:37 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 16
Model samsung SM-F966W
Model IDsamsung SM-F966W
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% 437
81.3 IPS
 
Image Classification (HP)
100% 21148
3.93 KIPS
 
Image Classification (Q)
97% 48520
9.05 KIPS
 
Image Segmentation (SP)
100% 539
8.74 IPS
 
Image Segmentation (HP)
100% 12538
203.2 IPS
 
Image Segmentation (Q)
98% 37210
605.1 IPS
 
Pose Estimation (SP)
100% 388
0.45 IPS
 
Pose Estimation (HP)
100% 109697
128.0 IPS
 
Pose Estimation (Q)
98% 476196
557.4 IPS
 
Object Detection (SP)
100% 251
19.9 IPS
 
Object Detection (HP)
100% 15889
1.26 KIPS
 
Object Detection (Q)
85% 18583
1.50 KIPS
 
Face Detection (SP)
100% 501
5.95 IPS
 
Face Detection (HP)
100% 33339
396.1 IPS
 
Face Detection (Q)
97% 106855
1.27 KIPS
 
Depth Estimation (SP)
100% 433
3.34 IPS
 
Depth Estimation (HP)
99% 72040
555.0 IPS
 
Depth Estimation (Q)
63% 128796
1.19 KIPS
 
Style Transfer (SP)
100% 790
1.02 IPS
 
Style Transfer (HP)
98% 90481
116.7 IPS
 
Style Transfer (Q)
98% 449814
580.0 IPS
 
Image Super-Resolution (SP)
100% 217
8.00 IPS
 
Image Super-Resolution (HP)
100% 49825
1.84 KIPS
 
Image Super-Resolution (Q)
97% 129330
4.79 KIPS
 
Text Classification (SP)
100% 363
484.6 IPS
 
Text Classification (HP)
100% 3840
5.13 KIPS
 
Text Classification (Q)
93% 7832
10.5 KIPS
 
Machine Translation (SP)
100% 481
8.29 IPS
 
Machine Translation (HP)
100% 3874
66.7 IPS
 
Machine Translation (Q)
56% 2767
71.3 IPS
 

Compare

Set Baseline Geekbench 6 now available