Geekbench AI Score

109
Single Precision Score
110
Half Precision Score
300
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 18 2024 07:38 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM ARMv8
System Information
Operating System Android 13
Model Google corsola
Model IDGoogle corsola
Motherboard kyogre
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.05 GHz
Memory Information
Size 6.99 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 64
12.0 IPS
 
Image Classification (HP)
100% 65
12.1 IPS
 
Image Classification (Q)
99% 193
36.0 IPS
 
Image Segmentation (SP)
100% 89
1.44 IPS
 
Image Segmentation (HP)
100% 89
1.45 IPS
 
Image Segmentation (Q)
98% 214
3.48 IPS
 
Pose Estimation (SP)
100% 111
0.13 IPS
 
Pose Estimation (HP)
100% 111
0.13 IPS
 
Pose Estimation (Q)
98% 476
0.56 IPS
 
Object Detection (SP)
100% 64
5.07 IPS
 
Object Detection (HP)
100% 64
5.08 IPS
 
Object Detection (Q)
87% 208
16.7 IPS
 
Face Detection (SP)
100% 183
2.17 IPS
 
Face Detection (HP)
100% 184
2.18 IPS
 
Face Detection (Q)
97% 439
5.23 IPS
 
Depth Estimation (SP)
100% 143
1.10 IPS
 
Depth Estimation (HP)
99% 144
1.11 IPS
 
Depth Estimation (Q)
64% 397
3.60 IPS
 
Style Transfer (SP)
100% 255
0.33 IPS
 
Style Transfer (HP)
100% 255
0.33 IPS
 
Style Transfer (Q)
98% 878
1.13 IPS
 
Image Super-Resolution (SP)
100% 68
2.52 IPS
 
Image Super-Resolution (HP)
100% 68
2.50 IPS
 
Image Super-Resolution (Q)
97% 274
10.2 IPS
 
Text Classification (SP)
100% 89
118.8 IPS
 
Text Classification (HP)
100% 89
119.2 IPS
 
Text Classification (Q)
91% 202
272.0 IPS
 
Machine Translation (SP)
100% 158
2.71 IPS
 
Machine Translation (HP)
100% 158
2.72 IPS
 
Machine Translation (Q)
57% 171
4.18 IPS
 

Compare

Set Baseline Geekbench 6 now available