Geekbench AI Score

552
Single Precision Score
550
Half Precision Score
1002
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

Upload Date November 07 2025 11:05 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Qualcomm
System Information
Operating System Android 13
Model samsung SM-A716U1
Model IDsamsung SM-A716U1
Motherboard lito
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 15 part 2052 revision 14
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 21 Core @ 2.21 GHz
Cluster 31 Core @ 2.40 GHz
Memory Information
Size 5.29 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 255
47.4 IPS
 
Image Classification (HP)
100% 255
47.4 IPS
 
Image Classification (Q)
100% 683
127.1 IPS
 
Image Segmentation (SP)
100% 310
5.03 IPS
 
Image Segmentation (HP)
100% 310
5.02 IPS
 
Image Segmentation (Q)
98% 756
12.3 IPS
 
Pose Estimation (SP)
100% 1191
1.39 IPS
 
Pose Estimation (HP)
100% 1172
1.37 IPS
 
Pose Estimation (Q)
84% 1677
1.99 IPS
 
Object Detection (SP)
100% 245
19.4 IPS
 
Object Detection (HP)
100% 249
19.8 IPS
 
Object Detection (Q)
83% 686
55.4 IPS
 
Face Detection (SP)
100% 771
9.16 IPS
 
Face Detection (HP)
100% 777
9.23 IPS
 
Face Detection (Q)
95% 1551
18.5 IPS
 
Depth Estimation (SP)
100% 973
7.50 IPS
 
Depth Estimation (HP)
99% 929
7.16 IPS
 
Depth Estimation (Q)
64% 1520
13.9 IPS
 
Style Transfer (SP)
89% 1940
2.52 IPS
 
Style Transfer (HP)
89% 1941
2.52 IPS
 
Style Transfer (Q)
98% 3845
4.96 IPS
 
Image Super-Resolution (SP)
100% 541
20.0 IPS
 
Image Super-Resolution (HP)
100% 548
20.3 IPS
 
Image Super-Resolution (Q)
97% 934
34.6 IPS
 
Text Classification (SP)
100% 290
386.7 IPS
 
Text Classification (HP)
100% 286
381.5 IPS
 
Text Classification (Q)
88% 554
747.1 IPS
 
Machine Translation (SP)
100% 502
8.64 IPS
 
Machine Translation (HP)
100% 503
8.66 IPS
 
Machine Translation (Q)
50% 369
13.1 IPS
 

Compare

Set Baseline Geekbench 6 now available