Geekbench AI Score

396
Single Precision Score
364
Half Precision Score
21028
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User epicgeek
Upload Date October 17 2024 07:45 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM ARMv8
System Information
Operating System Android 14
Model motorola motorola razr 50 ultra
Model IDmotorola motorola razr 50 ultra
Motherboard arcfox
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.01 GHz
Memory Information
Size 11.12 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 265
49.4 IPS
 
Image Classification (HP)
100% 273
50.7 IPS
 
Image Classification (Q)
97% 26222
4.89 KIPS
 
Image Segmentation (SP)
100% 333
5.39 IPS
 
Image Segmentation (HP)
100% 299
4.84 IPS
 
Image Segmentation (Q)
98% 17876
290.7 IPS
 
Pose Estimation (SP)
100% 398
0.46 IPS
 
Pose Estimation (HP)
100% 360
0.42 IPS
 
Pose Estimation (Q)
98% 134387
157.3 IPS
 
Object Detection (SP)
100% 239
19.0 IPS
 
Object Detection (HP)
100% 227
18.0 IPS
 
Object Detection (Q)
86% 11536
927.6 IPS
 
Face Detection (SP)
100% 576
6.85 IPS
 
Face Detection (HP)
100% 436
5.18 IPS
 
Face Detection (Q)
97% 61116
728.8 IPS
 
Depth Estimation (SP)
100% 448
3.45 IPS
 
Depth Estimation (HP)
99% 458
3.53 IPS
 
Depth Estimation (Q)
63% 58326
546.1 IPS
 
Style Transfer (SP)
100% 710
0.91 IPS
 
Style Transfer (HP)
100% 711
0.91 IPS
 
Style Transfer (Q)
98% 162903
210.1 IPS
 
Image Super-Resolution (SP)
100% 272
10.1 IPS
 
Image Super-Resolution (HP)
100% 240
8.88 IPS
 
Image Super-Resolution (Q)
97% 44147
1.64 KIPS
 
Text Classification (SP)
100% 356
475.0 IPS
 
Text Classification (HP)
100% 383
510.7 IPS
 
Text Classification (Q)
93% 5402
7.25 KIPS
 
Machine Translation (SP)
100% 653
11.2 IPS
 
Machine Translation (HP)
100% 473
8.15 IPS
 
Machine Translation (Q)
30% 168
33.8 IPS
 

Compare

Set Baseline Geekbench 6 now available