Geekbench AI Score

510
Single Precision Score
26581
Half Precision Score
60358
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

Upload Date October 27 2025 06:09 PM
Views 16

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% 418
77.7 IPS
 
Image Classification (HP)
100% 21024
3.91 KIPS
 
Image Classification (Q)
97% 49770
9.29 KIPS
 
Image Segmentation (SP)
100% 506
8.20 IPS
 
Image Segmentation (HP)
100% 13541
219.5 IPS
 
Image Segmentation (Q)
98% 41255
670.8 IPS
 
Pose Estimation (SP)
100% 470
0.55 IPS
 
Pose Estimation (HP)
100% 123217
143.8 IPS
 
Pose Estimation (Q)
98% 478745
560.3 IPS
 
Object Detection (SP)
100% 339
26.9 IPS
 
Object Detection (HP)
100% 17923
1.42 KIPS
 
Object Detection (Q)
85% 21894
1.76 KIPS
 
Face Detection (SP)
100% 671
7.97 IPS
 
Face Detection (HP)
100% 38853
461.7 IPS
 
Face Detection (Q)
97% 131870
1.57 KIPS
 
Depth Estimation (SP)
100% 571
4.40 IPS
 
Depth Estimation (HP)
99% 80557
620.6 IPS
 
Depth Estimation (Q)
63% 143665
1.33 KIPS
 
Style Transfer (SP)
100% 1013
1.30 IPS
 
Style Transfer (HP)
98% 98534
127.1 IPS
 
Style Transfer (Q)
98% 491732
634.1 IPS
 
Image Super-Resolution (SP)
100% 319
11.8 IPS
 
Image Super-Resolution (HP)
100% 53533
1.98 KIPS
 
Image Super-Resolution (Q)
97% 135036
5.00 KIPS
 
Text Classification (SP)
100% 458
611.2 IPS
 
Text Classification (HP)
100% 3888
5.19 KIPS
 
Text Classification (Q)
93% 8035
10.8 KIPS
 
Machine Translation (SP)
100% 623
10.7 IPS
 
Machine Translation (HP)
100% 4364
75.2 IPS
 
Machine Translation (Q)
56% 2950
76.0 IPS
 

Compare

Set Baseline Geekbench 6 now available