Geekbench AI Score

364
Single Precision Score
363
Half Precision Score
27523
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 22 2024 07:45 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM SM8635
System Information
Operating System Android 15
Model HONOR ROD2-W69
Model IDHONOR ROD2-W69
Motherboard pineapple
Governorwalt
CPU Information
Name ARM SM8635
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.01 GHz
Memory Information
Size 11.04 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 286
53.2 IPS
 
Image Classification (HP)
100% 290
53.9 IPS
 
Image Classification (Q)
97% 25268
4.72 KIPS
 
Image Segmentation (SP)
100% 368
5.96 IPS
 
Image Segmentation (HP)
100% 372
6.03 IPS
 
Image Segmentation (Q)
98% 18863
306.7 IPS
 
Pose Estimation (SP)
100% 282
0.33 IPS
 
Pose Estimation (HP)
100% 271
0.32 IPS
 
Pose Estimation (Q)
98% 139378
163.1 IPS
 
Object Detection (SP)
100% 151
11.9 IPS
 
Object Detection (HP)
100% 151
11.9 IPS
 
Object Detection (Q)
86% 11112
893.5 IPS
 
Face Detection (SP)
100% 425
5.05 IPS
 
Face Detection (HP)
100% 424
5.03 IPS
 
Face Detection (Q)
97% 56559
674.5 IPS
 
Depth Estimation (SP)
100% 358
2.75 IPS
 
Depth Estimation (HP)
99% 355
2.74 IPS
 
Depth Estimation (Q)
63% 59283
555.1 IPS
 
Style Transfer (SP)
100% 650
0.84 IPS
 
Style Transfer (HP)
100% 651
0.84 IPS
 
Style Transfer (Q)
98% 203699
262.7 IPS
 
Image Super-Resolution (SP)
100% 321
11.9 IPS
 
Image Super-Resolution (HP)
100% 318
11.7 IPS
 
Image Super-Resolution (Q)
97% 55125
2.04 KIPS
 
Text Classification (SP)
100% 430
574.0 IPS
 
Text Classification (HP)
100% 430
573.7 IPS
 
Text Classification (Q)
93% 5684
7.63 KIPS
 
Machine Translation (SP)
100% 680
11.7 IPS
 
Machine Translation (HP)
100% 682
11.7 IPS
 
Machine Translation (Q)
55% 1579
41.4 IPS
 

Compare

Set Baseline Geekbench 6 now available