Geekbench ML Score

2007
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 31 2023 01:38 PM
Views 4

System Information

System Information
Operating System Android 13
Model vivo V2241A
Model IDvivo V2241A
Motherboard k6985v1_64
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.85 GHz
Cluster 31 Core @ 3.05 GHz
Memory Information
Size 7.17 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 899
96.3 IPS
 
Image Classification (F16)
100% 4374
468.6 IPS
 
Image Classification (I8)
80% 11227
1.20 KIPS
 
Image Segmentation (F32)
100% 1067
6.59 IPS
 
Image Segmentation (F16)
100% 1909
11.8 IPS
 
Image Segmentation (I8)
89% 26620
164.4 IPS
 
Pose Estimation (F32)
100% 849
3.44 IPS
 
Pose Estimation (F16)
100% 2360
9.55 IPS
 
Pose Estimation (I8)
80% 8841
35.8 IPS
 
Object Detection (F32)
100% 864
30.3 IPS
 
Object Detection (F16)
100% 1677
58.8 IPS
 
Object Detection (I8)
53% 2075
72.8 IPS
 
Face Detection (F32)
25% 440
5.05 IPS
 
Face Detection (F16)
97% 3229
37.1 IPS
 
Face Detection (I8)
75% 19659
225.9 IPS
 
Text Classification (F32)
52% 134
53.1 IPS
 
Text Classification (F16)
100% 1324
523.7 IPS
 
Machine Translation (F32)
100% 947
145.9 IPS
 
Machine Translation (F16)
100% 938
144.6 IPS
 

Compare

Set Baseline Geekbench 6 now available