Geekbench ML Score

592
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 13 2024 08:26 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 NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 628
67.3 IPS
 
Image Classification (F16)
100% 790
84.7 IPS
 
Image Classification (I8)
80% 2245
240.5 IPS
 
Image Segmentation (F32)
100% 714
4.41 IPS
 
Image Segmentation (F16)
100% 746
4.61 IPS
 
Image Segmentation (I8)
89% 4386
27.1 IPS
 
Pose Estimation (F32)
100% 356
1.44 IPS
 
Pose Estimation (F16)
100% 843
3.41 IPS
 
Pose Estimation (I8)
80% 3271
13.2 IPS
 
Object Detection (F32)
100% 372
13.1 IPS
 
Object Detection (F16)
100% 471
16.5 IPS
 
Object Detection (I8)
52% 875
30.7 IPS
 
Face Detection (F32)
100% 818
9.40 IPS
 
Face Detection (F16)
97% 1206
13.9 IPS
 
Face Detection (I8)
75% 3068
35.3 IPS
 
Text Classification (F32)
54% 16
6.46 IPS
 
Text Classification (F16)
54% 13
5.28 IPS
 
Machine Translation (F32)
100% 438
67.5 IPS
 
Machine Translation (F16)
100% 443
68.3 IPS
 

Compare

Set Baseline Geekbench 6 now available