Geekbench ML Score

989
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date September 26 2024 02:50 AM
Views 1

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% 465
86.9 IPS
 
Image Classification (F16)
100% 461
86.2 IPS
 
Image Classification (I8)
97% 865
161.8 IPS
 
Image Segmentation (F32)
100% 593
9.91 IPS
 
Image Segmentation (F16)
100% 570
9.52 IPS
 
Image Segmentation (I8)
98% 697
11.6 IPS
 
Pose Estimation (F32)
100% 1039
1.26 IPS
 
Pose Estimation (F16)
100% 1016
1.23 IPS
 
Pose Estimation (I8)
100% 4893
5.92 IPS
 
Object Detection (F32)
100% 510
38.1 IPS
 
Object Detection (F16)
100% 507
37.9 IPS
 
Object Detection (I8)
61% 1228
91.6 IPS
 
Face Detection (F32)
100% 1088
12.9 IPS
 
Face Detection (F16)
100% 1086
12.9 IPS
 
Face Detection (I8)
86% 1956
23.3 IPS
 
Depth Estimation (F32)
100% 1088
8.44 IPS
 
Depth Estimation (F16)
100% 1098
8.51 IPS
 
Depth Estimation (I8)
95% 2102
16.3 IPS
 
Style Transfer (F32)
100% 2090
2.75 IPS
 
Style Transfer (F16)
100% 2106
2.77 IPS
 
Style Transfer (I8)
98% 5172
6.80 IPS
 
Image Super-Resolution (F32)
100% 706
25.2 IPS
 
Image Super-Resolution (F16)
100% 739
26.4 IPS
 
Image Super-Resolution (I8)
98% 1791
64.0 IPS
 
Text Classification (F32)
100% 540
776.4 IPS
 
Text Classification (F16)
100% 536
770.2 IPS
 
Text Classification (I8)
92% 403
579.7 IPS
 
Machine Translation (F32)
100% 1161
21.4 IPS
 
Machine Translation (F16)
100% 1137
20.9 IPS
 
Machine Translation (I8)
64% 533
9.80 IPS
 

Compare

Set Baseline Geekbench 6 now available