Geekbench AI Score

143
Single Precision Score
196
Half Precision Score
188
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 27 2025 09:34 AM
Views 8

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 15
Model Xiaomi 25040RP0AE
Model IDXiaomi 25040RP0AE
Motherboard taiko
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.20 GHz
Memory Information
Size 7.64 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 98
18.2 IPS
 
Image Classification (HP)
100% 166
30.9 IPS
 
Image Classification (Q)
99% 157
29.2 IPS
 
Image Segmentation (SP)
100% 118
1.92 IPS
 
Image Segmentation (HP)
100% 199
3.23 IPS
 
Image Segmentation (Q)
98% 189
3.07 IPS
 
Pose Estimation (SP)
100% 92
0.11 IPS
 
Pose Estimation (HP)
100% 108
0.13 IPS
 
Pose Estimation (Q)
96% 108
0.13 IPS
 
Object Detection (SP)
100% 70
5.58 IPS
 
Object Detection (HP)
100% 111
8.80 IPS
 
Object Detection (Q)
83% 97
7.85 IPS
 
Face Detection (SP)
100% 225
2.68 IPS
 
Face Detection (HP)
100% 336
3.99 IPS
 
Face Detection (Q)
97% 332
3.96 IPS
 
Depth Estimation (SP)
100% 174
1.34 IPS
 
Depth Estimation (HP)
99% 228
1.76 IPS
 
Depth Estimation (Q)
62% 184
1.74 IPS
 
Style Transfer (SP)
100% 350
0.45 IPS
 
Style Transfer (HP)
100% 488
0.63 IPS
 
Style Transfer (Q)
98% 486
0.63 IPS
 
Image Super-Resolution (SP)
100% 90
3.31 IPS
 
Image Super-Resolution (HP)
100% 139
5.13 IPS
 
Image Super-Resolution (Q)
97% 137
5.08 IPS
 
Text Classification (SP)
100% 156
208.7 IPS
 
Text Classification (HP)
100% 155
207.2 IPS
 
Text Classification (Q)
91% 247
331.9 IPS
 
Machine Translation (SP)
100% 266
4.59 IPS
 
Machine Translation (HP)
100% 267
4.60 IPS
 
Machine Translation (Q)
57% 179
4.38 IPS
 

Compare

Set Baseline Geekbench 6 now available