Geekbench AI Score

366
Single Precision Score
334
Half Precision Score
702
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 16 2024 01:11 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model motorola motorola edge 50 fusion
Model IDmotorola motorola edge 50 fusion
Motherboard cuscoi
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 2
Base Frequency 1.96 GHz
Cluster 14 Cores @ 1.96 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 7.29 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 170
31.7 IPS
 
Image Classification (HP)
100% 164
30.4 IPS
 
Image Classification (Q)
100% 470
87.4 IPS
 
Image Segmentation (SP)
100% 202
3.27 IPS
 
Image Segmentation (HP)
100% 197
3.19 IPS
 
Image Segmentation (Q)
98% 529
8.60 IPS
 
Pose Estimation (SP)
100% 734
0.86 IPS
 
Pose Estimation (HP)
100% 714
0.83 IPS
 
Pose Estimation (Q)
84% 1219
1.45 IPS
 
Object Detection (SP)
100% 171
13.6 IPS
 
Object Detection (HP)
100% 169
13.4 IPS
 
Object Detection (Q)
83% 615
49.7 IPS
 
Face Detection (SP)
100% 568
6.75 IPS
 
Face Detection (HP)
100% 395
4.70 IPS
 
Face Detection (Q)
95% 987
11.8 IPS
 
Depth Estimation (SP)
100% 855
6.59 IPS
 
Depth Estimation (HP)
99% 564
4.35 IPS
 
Depth Estimation (Q)
64% 1122
10.3 IPS
 
Style Transfer (SP)
89% 1303
1.69 IPS
 
Style Transfer (HP)
89% 1289
1.67 IPS
 
Style Transfer (Q)
98% 3921
5.06 IPS
 
Image Super-Resolution (SP)
100% 307
11.3 IPS
 
Image Super-Resolution (HP)
100% 305
11.3 IPS
 
Image Super-Resolution (Q)
97% 684
25.4 IPS
 
Text Classification (SP)
100% 175
233.0 IPS
 
Text Classification (HP)
100% 175
233.3 IPS
 
Text Classification (Q)
88% 278
375.6 IPS
 
Machine Translation (SP)
100% 295
5.07 IPS
 
Machine Translation (HP)
100% 291
5.02 IPS
 
Machine Translation (Q)
50% 190
6.73 IPS
 

Compare

Set Baseline Geekbench 6 now available