Geekbench AI Score

85
Single Precision Score
85
Half Precision Score
143
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date April 20 2025 03:28 PM
Views 8

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM Unisoc
System Information
Operating System Android 12
Model BLU M10L Pro
Model IDBLU M10L Pro
Motherboard ums312_2h10
Governorschedutil
CPU Information
Name ARM Unisoc
Topology 1 Processor, 4 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.82 GHz
Cluster 13 Cores @ 1.82 GHz
Cluster 21 Core @ 2.00 GHz
Memory Information
Size 2.72 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 48
8.93 IPS
 
Image Classification (HP)
100% 48
9.01 IPS
 
Image Classification (Q)
99% 91
17.0 IPS
 
Image Segmentation (SP)
100% 66
1.07 IPS
 
Image Segmentation (HP)
100% 66
1.08 IPS
 
Image Segmentation (Q)
98% 109
1.77 IPS
 
Pose Estimation (SP)
100% 95
0.11 IPS
 
Pose Estimation (HP)
100% 94
0.11 IPS
 
Pose Estimation (Q)
98% 199
0.23 IPS
 
Object Detection (SP)
100% 48
3.85 IPS
 
Object Detection (HP)
100% 49
3.87 IPS
 
Object Detection (Q)
87% 93
7.49 IPS
 
Face Detection (SP)
100% 127
1.51 IPS
 
Face Detection (HP)
100% 130
1.54 IPS
 
Face Detection (Q)
97% 239
2.85 IPS
 
Depth Estimation (SP)
100% 114
0.88 IPS
 
Depth Estimation (HP)
99% 116
0.89 IPS
 
Depth Estimation (Q)
64% 187
1.70 IPS
 
Style Transfer (SP)
100% 210
0.27 IPS
 
Style Transfer (HP)
100% 211
0.27 IPS
 
Style Transfer (Q)
98% 424
0.55 IPS
 
Image Super-Resolution (SP)
100% 58
2.13 IPS
 
Image Super-Resolution (HP)
100% 58
2.13 IPS
 
Image Super-Resolution (Q)
97% 119
4.40 IPS
 
Text Classification (SP)
100% 67
89.1 IPS
 
Text Classification (HP)
100% 67
88.8 IPS
 
Text Classification (Q)
91% 102
137.3 IPS
 
Machine Translation (SP)
100% 121
2.08 IPS
 
Machine Translation (HP)
100% 121
2.08 IPS
 
Machine Translation (Q)
57% 87
2.13 IPS
 

Compare

Set Baseline Geekbench 6 now available