Geekbench AI Score

448
Single Precision Score
450
Half Precision Score
864
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 18 2024 01:22 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
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% 204
38.0 IPS
 
Image Classification (HP)
100% 204
37.9 IPS
 
Image Classification (Q)
100% 587
109.2 IPS
 
Image Segmentation (SP)
100% 253
4.11 IPS
 
Image Segmentation (HP)
100% 252
4.08 IPS
 
Image Segmentation (Q)
98% 641
10.4 IPS
 
Pose Estimation (SP)
100% 975
1.14 IPS
 
Pose Estimation (HP)
100% 976
1.14 IPS
 
Pose Estimation (Q)
84% 1522
1.81 IPS
 
Object Detection (SP)
100% 196
15.5 IPS
 
Object Detection (HP)
100% 197
15.7 IPS
 
Object Detection (Q)
83% 585
47.3 IPS
 
Face Detection (SP)
100% 621
7.37 IPS
 
Face Detection (HP)
100% 618
7.35 IPS
 
Face Detection (Q)
95% 1333
15.9 IPS
 
Depth Estimation (SP)
100% 777
5.99 IPS
 
Depth Estimation (HP)
99% 807
6.21 IPS
 
Depth Estimation (Q)
64% 1384
12.7 IPS
 
Style Transfer (SP)
89% 1661
2.16 IPS
 
Style Transfer (HP)
89% 1675
2.17 IPS
 
Style Transfer (Q)
98% 3498
4.51 IPS
 
Image Super-Resolution (SP)
100% 418
15.4 IPS
 
Image Super-Resolution (HP)
100% 417
15.4 IPS
 
Image Super-Resolution (Q)
97% 836
31.0 IPS
 
Text Classification (SP)
100% 241
321.9 IPS
 
Text Classification (HP)
100% 240
320.4 IPS
 
Text Classification (Q)
88% 444
598.3 IPS
 
Machine Translation (SP)
100% 415
7.16 IPS
 
Machine Translation (HP)
100% 413
7.12 IPS
 
Machine Translation (Q)
50% 289
10.3 IPS
 

Compare

Set Baseline Geekbench 6 now available