Geekbench AI Score

510
Single Precision Score
503
Half Precision Score
950
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 14 2025 01:23 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model motorola moto g84 5G
Model IDmotorola moto g84 5G
Motherboard bangkk
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 11.24 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 239
44.5 IPS
 
Image Classification (HP)
100% 239
44.5 IPS
 
Image Classification (Q)
100% 726
135.0 IPS
 
Image Segmentation (SP)
100% 312
5.06 IPS
 
Image Segmentation (HP)
100% 312
5.06 IPS
 
Image Segmentation (Q)
98% 830
13.5 IPS
 
Pose Estimation (SP)
100% 1191
1.39 IPS
 
Pose Estimation (HP)
100% 1072
1.25 IPS
 
Pose Estimation (Q)
84% 1501
1.78 IPS
 
Object Detection (SP)
100% 211
16.7 IPS
 
Object Detection (HP)
100% 211
16.7 IPS
 
Object Detection (Q)
83% 617
49.9 IPS
 
Face Detection (SP)
100% 712
8.46 IPS
 
Face Detection (HP)
100% 715
8.50 IPS
 
Face Detection (Q)
95% 1493
17.8 IPS
 
Depth Estimation (SP)
100% 946
7.29 IPS
 
Depth Estimation (HP)
99% 941
7.25 IPS
 
Depth Estimation (Q)
64% 1405
12.9 IPS
 
Style Transfer (SP)
89% 1801
2.34 IPS
 
Style Transfer (HP)
89% 1798
2.33 IPS
 
Style Transfer (Q)
98% 3574
4.61 IPS
 
Image Super-Resolution (SP)
100% 494
18.2 IPS
 
Image Super-Resolution (HP)
100% 492
18.2 IPS
 
Image Super-Resolution (Q)
97% 868
32.2 IPS
 
Text Classification (SP)
100% 252
336.8 IPS
 
Text Classification (HP)
100% 247
329.7 IPS
 
Text Classification (Q)
88% 496
668.7 IPS
 
Machine Translation (SP)
100% 424
7.30 IPS
 
Machine Translation (HP)
100% 423
7.29 IPS
 
Machine Translation (Q)
50% 335
11.9 IPS
 

Compare

Set Baseline Geekbench 6 now available