Geekbench AI Score

104
Single Precision Score
126
Half Precision Score
125
Quantized Score
Geekbench AI 1.6.1 for Android AArch64

Result Information

Upload Date December 23 2025 11:33 AM
Views 11

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 16
Model Raspberry Pi 5 Model B Rev 1.0
Model IDRaspberry Pi 5 Model B Rev 1.0
Motherboard bcm2712
Governorperformance
CPU Information
Name ARM ARMv8
Topology 1 Processor, 4 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 1
Base Frequency 3.00 GHz
Cluster 14 Cores @ 3.00 GHz
Memory Information
Size 7.75 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 47
8.81 IPS
 
Image Classification (HP)
100% 66
12.3 IPS
 
Image Classification (Q)
96% 64
12.0 IPS
 
Image Segmentation (SP)
100% 65
1.06 IPS
 
Image Segmentation (HP)
100% 90
1.46 IPS
 
Image Segmentation (Q)
98% 88
1.43 IPS
 
Pose Estimation (SP)
100% 91
0.11 IPS
 
Pose Estimation (HP)
100% 112
0.13 IPS
 
Pose Estimation (Q)
94% 111
0.13 IPS
 
Object Detection (SP)
100% 37
2.97 IPS
 
Object Detection (HP)
100% 48
3.79 IPS
 
Object Detection (Q)
86% 46
3.66 IPS
 
Face Detection (SP)
100% 128
1.52 IPS
 
Face Detection (HP)
100% 165
1.96 IPS
 
Face Detection (Q)
96% 156
1.87 IPS
 
Depth Estimation (SP)
100% 108
0.83 IPS
 
Depth Estimation (HP)
99% 128
0.99 IPS
 
Depth Estimation (Q)
63% 105
0.99 IPS
 
Style Transfer (SP)
100% 275
0.35 IPS
 
Style Transfer (HP)
100% 334
0.43 IPS
 
Style Transfer (Q)
98% 332
0.43 IPS
 
Image Super-Resolution (SP)
100% 63
2.33 IPS
 
Image Super-Resolution (HP)
100% 77
2.84 IPS
 
Image Super-Resolution (Q)
97% 75
2.79 IPS
 
Text Classification (SP)
100% 207
276.2 IPS
 
Text Classification (HP)
100% 205
273.5 IPS
 
Text Classification (Q)
91% 362
487.1 IPS
 
Machine Translation (SP)
100% 297
5.12 IPS
 
Machine Translation (HP)
100% 290
5.00 IPS
 
Machine Translation (Q)
57% 235
5.74 IPS
 

Compare

Set Baseline Geekbench 6 now available