Geekbench AI Score

126
Single Precision Score
129
Half Precision Score
170
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date April 20 2025 02:43 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
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% 55
10.3 IPS
 
Image Classification (HP)
100% 56
10.4 IPS
 
Image Classification (Q)
100% 114
21.1 IPS
 
Image Segmentation (SP)
100% 69
1.13 IPS
 
Image Segmentation (HP)
100% 69
1.12 IPS
 
Image Segmentation (Q)
98% 134
2.19 IPS
 
Pose Estimation (SP)
100% 276
0.32 IPS
 
Pose Estimation (HP)
100% 277
0.32 IPS
 
Pose Estimation (Q)
84% 202
0.24 IPS
 
Object Detection (SP)
100% 55
4.40 IPS
 
Object Detection (HP)
100% 55
4.40 IPS
 
Object Detection (Q)
83% 110
8.89 IPS
 
Face Detection (SP)
100% 188
2.24 IPS
 
Face Detection (HP)
100% 188
2.24 IPS
 
Face Detection (Q)
95% 303
3.62 IPS
 
Depth Estimation (SP)
100% 174
1.34 IPS
 
Depth Estimation (HP)
99% 231
1.78 IPS
 
Depth Estimation (Q)
64% 240
2.20 IPS
 
Style Transfer (SP)
89% 441
0.57 IPS
 
Style Transfer (HP)
89% 441
0.57 IPS
 
Style Transfer (Q)
98% 548
0.71 IPS
 
Image Super-Resolution (SP)
100% 132
4.88 IPS
 
Image Super-Resolution (HP)
100% 132
4.88 IPS
 
Image Super-Resolution (Q)
97% 134
4.96 IPS
 
Text Classification (SP)
100% 70
93.4 IPS
 
Text Classification (HP)
100% 70
93.4 IPS
 
Text Classification (Q)
88% 116
156.6 IPS
 
Machine Translation (SP)
100% 133
2.28 IPS
 
Machine Translation (HP)
100% 132
2.27 IPS
 
Machine Translation (Q)
50% 99
3.52 IPS
 

Compare

Set Baseline Geekbench 6 now available