Geekbench AI Score

133
Single Precision Score
143
Half Precision Score
153
Quantized Score
Geekbench AI 1.0.0 for Android AArch64

Result Information

Upload Date August 22 2024 05:17 AM
Views 11

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM Unisoc
System Information
Operating System Android 13
Model INFINIX Infinix X6528
Model IDINFINIX Infinix X6528
Motherboard Infinix-X6528
Governorschedutil
CPU Information
Name ARM Unisoc
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.61 GHz
Cluster 18 Cores @ 1.61 GHz
Memory Information
Size 7.59 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 79
14.7 IPS
 
Image Classification (HP)
100% 80
14.8 IPS
 
Image Classification (Q)
99% 107
19.9 IPS
 
Image Segmentation (SP)
100% 103
1.67 IPS
 
Image Segmentation (HP)
100% 103
1.67 IPS
 
Image Segmentation (Q)
98% 141
2.30 IPS
 
Pose Estimation (SP)
100% 467
0.54 IPS
 
Pose Estimation (HP)
100% 466
0.54 IPS
 
Pose Estimation (Q)
96% 427
0.50 IPS
 
Object Detection (SP)
100% 41
3.29 IPS
 
Object Detection (HP)
100% 42
3.30 IPS
 
Object Detection (Q)
89% 79
6.29 IPS
 
Face Detection (SP)
100% 262
3.12 IPS
 
Face Detection (HP)
100% 266
3.15 IPS
 
Face Detection (Q)
97% 203
2.42 IPS
 
Depth Estimation (SP)
100% 369
2.84 IPS
 
Depth Estimation (HP)
100% 370
2.85 IPS
 
Depth Estimation (Q)
82% 386
3.04 IPS
 
Style Transfer (SP)
100% 330
0.42 IPS
 
Style Transfer (HP)
100% 188
0.24 IPS
 
Style Transfer (Q)
98% 561
0.72 IPS
 
Image Super-Resolution (SP)
100% 201
7.42 IPS
 
Image Super-Resolution (HP)
100% 203
7.48 IPS
 
Image Super-Resolution (Q)
97% 214
7.92 IPS
 
Text Classification (SP)
100% 25
33.9 IPS
 
Text Classification (HP)
100% 59
79.0 IPS
 
Text Classification (Q)
93% 32
42.8 IPS
 
Machine Translation (SP)
100% 74
1.27 IPS
 
Machine Translation (HP)
100% 105
1.81 IPS
 
Machine Translation (Q)
55% 48
1.28 IPS
 

Compare

Set Baseline Geekbench 6 now available