Geekbench AI Score

879
Single Precision Score
878
Half Precision Score
1886
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 02 2025 11:07 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 cusco
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 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.21 GHz
Memory Information
Size 7.29 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 427
79.5 IPS
 
Image Classification (HP)
100% 425
79.1 IPS
 
Image Classification (Q)
100% 1346
250.3 IPS
 
Image Segmentation (SP)
100% 501
8.12 IPS
 
Image Segmentation (HP)
100% 506
8.21 IPS
 
Image Segmentation (Q)
98% 1563
25.4 IPS
 
Pose Estimation (SP)
100% 1971
2.30 IPS
 
Pose Estimation (HP)
100% 1969
2.30 IPS
 
Pose Estimation (Q)
84% 3475
4.12 IPS
 
Object Detection (SP)
100% 431
34.2 IPS
 
Object Detection (HP)
100% 427
33.8 IPS
 
Object Detection (Q)
83% 1299
104.9 IPS
 
Face Detection (SP)
100% 1085
12.9 IPS
 
Face Detection (HP)
100% 1096
13.0 IPS
 
Face Detection (Q)
95% 3190
38.1 IPS
 
Depth Estimation (SP)
100% 1464
11.3 IPS
 
Depth Estimation (HP)
99% 1462
11.3 IPS
 
Depth Estimation (Q)
64% 3173
29.1 IPS
 
Style Transfer (SP)
89% 3483
4.52 IPS
 
Style Transfer (HP)
89% 3496
4.54 IPS
 
Style Transfer (Q)
98% 7977
10.3 IPS
 
Image Super-Resolution (SP)
100% 841
31.1 IPS
 
Image Super-Resolution (HP)
100% 852
31.4 IPS
 
Image Super-Resolution (Q)
97% 1897
70.3 IPS
 
Text Classification (SP)
100% 472
630.1 IPS
 
Text Classification (HP)
100% 467
622.8 IPS
 
Text Classification (Q)
88% 872
1.18 KIPS
 
Machine Translation (SP)
100% 697
12.0 IPS
 
Machine Translation (HP)
100% 683
11.8 IPS
 
Machine Translation (Q)
50% 451
16.0 IPS
 

Compare

Set Baseline Geekbench 6 now available