Geekbench ML Score

1636
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date November 27 2024 04:49 PM
Views 1

System Information

System Information
Operating System Android 15
Model OnePlus PJZ110
Model IDOnePlus PJZ110
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 1 revision 4
Base Frequency 3.53 GHz
Cluster 16 Cores @ 3.53 GHz
Cluster 22 Cores @ 4.32 GHz
Memory Information
Size 10.86 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 936
175.1 IPS
 
Image Classification (F16)
100% 1033
193.3 IPS
 
Image Classification (I8)
97% 1518
284.1 IPS
 
Image Segmentation (F32)
100% 1442
24.1 IPS
 
Image Segmentation (F16)
100% 1460
24.4 IPS
 
Image Segmentation (I8)
98% 1468
24.5 IPS
 
Pose Estimation (F32)
100% 1839
2.23 IPS
 
Pose Estimation (F16)
100% 1822
2.21 IPS
 
Pose Estimation (I8)
100% 8241
9.98 IPS
 
Object Detection (F32)
100% 1032
77.0 IPS
 
Object Detection (F16)
100% 1119
83.6 IPS
 
Object Detection (I8)
61% 2353
175.6 IPS
 
Face Detection (F32)
100% 1963
23.3 IPS
 
Face Detection (F16)
100% 1979
23.5 IPS
 
Face Detection (I8)
86% 3765
44.8 IPS
 
Depth Estimation (F32)
100% 1960
15.2 IPS
 
Depth Estimation (F16)
100% 1956
15.2 IPS
 
Depth Estimation (I8)
95% 4792
37.2 IPS
 
Style Transfer (F32)
100% 3136
4.12 IPS
 
Style Transfer (F16)
100% 3088
4.06 IPS
 
Style Transfer (I8)
98% 7647
10.1 IPS
 
Image Super-Resolution (F32)
100% 1268
45.3 IPS
 
Image Super-Resolution (F16)
100% 1323
47.2 IPS
 
Image Super-Resolution (I8)
98% 3595
128.4 IPS
 
Text Classification (F32)
100% 729
1.05 KIPS
 
Text Classification (F16)
100% 316
454.1 IPS
 
Text Classification (I8)
92% 828
1.19 KIPS
 
Machine Translation (F32)
100% 617
11.3 IPS
 
Machine Translation (F16)
100% 773
14.2 IPS
 
Machine Translation (I8)
64% 710
13.1 IPS
 

Compare

Set Baseline Geekbench 6 now available