Geekbench AI Score

200
Single Precision Score
200
Half Precision Score
426
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 12 2025 04:43 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM ARMv8
System Information
Operating System Android 13
Model rockchip orangepi5ultra
Model IDrockchip orangepi5ultra
Motherboard rk30sdk
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.30 GHz
Cluster 32 Cores @ 2.35 GHz
Memory Information
Size 15.57 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 120
22.3 IPS
 
Image Classification (HP)
100% 120
22.3 IPS
 
Image Classification (Q)
99% 268
50.0 IPS
 
Image Segmentation (SP)
100% 159
2.57 IPS
 
Image Segmentation (HP)
100% 160
2.60 IPS
 
Image Segmentation (Q)
98% 292
4.75 IPS
 
Pose Estimation (SP)
100% 214
0.25 IPS
 
Pose Estimation (HP)
100% 213
0.25 IPS
 
Pose Estimation (Q)
98% 805
0.94 IPS
 
Object Detection (SP)
100% 119
9.42 IPS
 
Object Detection (HP)
100% 118
9.37 IPS
 
Object Detection (Q)
87% 294
23.5 IPS
 
Face Detection (SP)
100% 304
3.61 IPS
 
Face Detection (HP)
100% 308
3.66 IPS
 
Face Detection (Q)
97% 606
7.22 IPS
 
Depth Estimation (SP)
100% 258
1.98 IPS
 
Depth Estimation (HP)
99% 258
1.99 IPS
 
Depth Estimation (Q)
64% 566
5.13 IPS
 
Style Transfer (SP)
100% 430
0.55 IPS
 
Style Transfer (HP)
100% 429
0.55 IPS
 
Style Transfer (Q)
98% 1278
1.65 IPS
 
Image Super-Resolution (SP)
100% 126
4.64 IPS
 
Image Super-Resolution (HP)
100% 125
4.63 IPS
 
Image Super-Resolution (Q)
97% 455
16.8 IPS
 
Text Classification (SP)
100% 173
230.4 IPS
 
Text Classification (HP)
100% 172
229.3 IPS
 
Text Classification (Q)
91% 277
371.8 IPS
 
Machine Translation (SP)
100% 293
5.04 IPS
 
Machine Translation (HP)
100% 297
5.12 IPS
 
Machine Translation (Q)
57% 196
4.80 IPS
 

Compare

Set Baseline Geekbench 6 now available