Geekbench ML Score

321
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 13 2024 08:20 AM
Views 1

System Information

System Information
Operating System Android 11
Model Sony Xperia 1
Model IDSony J9110
Motherboard msmnile
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 13 part 2052 revision 14
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 5.36 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 232
24.9 IPS
 
Image Classification (F16)
100% 235
25.2 IPS
 
Image Classification (I8)
81% 170
18.2 IPS
 
Image Segmentation (F32)
100% 446
2.75 IPS
 
Image Segmentation (F16)
100% 441
2.73 IPS
 
Image Segmentation (I8)
89% 745
4.60 IPS
 
Pose Estimation (F32)
100% 217
0.88 IPS
 
Pose Estimation (F16)
100% 196
0.79 IPS
 
Pose Estimation (I8)
80% 191
0.77 IPS
 
Object Detection (F32)
100% 332
11.7 IPS
 
Object Detection (F16)
100% 320
11.2 IPS
 
Object Detection (I8)
52% 232
8.15 IPS
 
Face Detection (F32)
100% 470
5.40 IPS
 
Face Detection (F16)
100% 461
5.29 IPS
 
Face Detection (I8)
75% 463
5.32 IPS
 
Text Classification (F32)
100% 289
114.2 IPS
 
Text Classification (F16)
100% 290
114.8 IPS
 
Machine Translation (F32)
100% 444
68.5 IPS
 
Machine Translation (F16)
100% 426
65.7 IPS
 

Compare

Set Baseline Geekbench 6 now available