Geekbench ML Score

972
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date September 25 2024 08:11 AM
Views 2

System Information

System Information
Operating System Android 14
Model OnePlus PJF110
Model IDOnePlus PJF110
Motherboard pineapple
Governoruag
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 1.90 GHz
Cluster 13 Cores @ 1.90 GHz
Cluster 24 Cores @ 2.61 GHz
Cluster 31 Core @ 2.80 GHz
Memory Information
Size 14.96 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 423
79.2 IPS
 
Image Classification (F16)
100% 463
86.7 IPS
 
Image Classification (I8)
97% 800
149.7 IPS
 
Image Segmentation (F32)
100% 596
9.95 IPS
 
Image Segmentation (F16)
100% 598
9.99 IPS
 
Image Segmentation (I8)
98% 589
9.83 IPS
 
Pose Estimation (F32)
100% 1048
1.27 IPS
 
Pose Estimation (F16)
100% 1014
1.23 IPS
 
Pose Estimation (I8)
100% 4648
5.63 IPS
 
Object Detection (F32)
100% 508
37.9 IPS
 
Object Detection (F16)
100% 504
37.6 IPS
 
Object Detection (I8)
61% 1084
80.9 IPS
 
Face Detection (F32)
100% 1087
12.9 IPS
 
Face Detection (F16)
100% 1124
13.4 IPS
 
Face Detection (I8)
86% 2011
23.9 IPS
 
Depth Estimation (F32)
100% 1088
8.44 IPS
 
Depth Estimation (F16)
100% 1113
8.63 IPS
 
Depth Estimation (I8)
95% 2102
16.3 IPS
 
Style Transfer (F32)
100% 2092
2.75 IPS
 
Style Transfer (F16)
100% 2116
2.78 IPS
 
Style Transfer (I8)
98% 4714
6.20 IPS
 
Image Super-Resolution (F32)
100% 711
25.4 IPS
 
Image Super-Resolution (F16)
100% 731
26.1 IPS
 
Image Super-Resolution (I8)
98% 1772
63.3 IPS
 
Text Classification (F32)
100% 530
761.9 IPS
 
Text Classification (F16)
100% 529
760.0 IPS
 
Text Classification (I8)
92% 379
545.4 IPS
 
Machine Translation (F32)
100% 1171
21.5 IPS
 
Machine Translation (F16)
100% 1163
21.4 IPS
 
Machine Translation (I8)
64% 546
10.0 IPS
 

Compare

Set Baseline Geekbench 6 now available