Geekbench AI Score

86
Single Precision Score
87
Half Precision Score
411
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User WB_Mochi0
Upload Date September 10 2025 07:07 AM
Views 11

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM ARMv8
System Information
Operating System Android 13
Model QUALCOMM FiiO JM21
Model IDQUALCOMM FiiO JM21
Motherboard bengal
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3337 revision 0
Base Frequency 1.90 GHz
Cluster 14 Cores @ 1.90 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 2.59 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 49
9.13 IPS
 
Image Classification (HP)
100% 49
9.16 IPS
 
Image Classification (Q)
96% 495
92.4 IPS
 
Image Segmentation (SP)
100% 66
1.07 IPS
 
Image Segmentation (HP)
100% 67
1.09 IPS
 
Image Segmentation (Q)
98% 658
10.7 IPS
 
Pose Estimation (SP)
100% 94
0.11 IPS
 
Pose Estimation (HP)
100% 94
0.11 IPS
 
Pose Estimation (Q)
96% 3390
3.97 IPS
 
Object Detection (SP)
100% 49
3.88 IPS
 
Object Detection (HP)
100% 49
3.91 IPS
 
Object Detection (Q)
84% 570
46.0 IPS
 
Face Detection (SP)
100% 127
1.51 IPS
 
Face Detection (HP)
100% 129
1.53 IPS
 
Face Detection (Q)
97% 1135
13.5 IPS
 
Depth Estimation (SP)
100% 114
0.87 IPS
 
Depth Estimation (HP)
99% 114
0.88 IPS
 
Depth Estimation (Q)
64% 2115
19.4 IPS
 
Style Transfer (SP)
100% 211
0.27 IPS
 
Style Transfer (HP)
100% 210
0.27 IPS
 
Style Transfer (Q)
98% 5712
7.37 IPS
 
Image Super-Resolution (SP)
100% 56
2.07 IPS
 
Image Super-Resolution (HP)
100% 56
2.07 IPS
 
Image Super-Resolution (Q)
97% 105
3.88 IPS
 
Text Classification (SP)
100% 74
98.9 IPS
 
Text Classification (HP)
100% 75
99.6 IPS
 
Text Classification (Q)
93% 155
208.8 IPS
 
Machine Translation (SP)
100% 127
2.18 IPS
 
Machine Translation (HP)
100% 130
2.25 IPS
 
Machine Translation (Q)
0% 0
1.07 IPS
 

Compare

Set Baseline Geekbench 6 now available