Geekbench AI Score

3083
Single Precision Score
3055
Half Precision Score
5116
Quantized Score
Geekbench AI 1.0.0 for Android AArch64

Result Information

User hass
Upload Date September 05 2024 03:04 PM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model nubia NX769J
Model IDnubia NX769J
Motherboard pineapple
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.26 GHz
Cluster 12 Cores @ 2.27 GHz
Cluster 22 Cores @ 2.96 GHz
Cluster 33 Cores @ 3.15 GHz
Cluster 41 Core @ 3.40 GHz
Memory Information
Size 14.99 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2041
379.6 IPS
 
Image Classification (HP)
100% 2084
387.5 IPS
 
Image Classification (Q)
100% 3901
725.4 IPS
 
Image Segmentation (SP)
100% 2659
43.1 IPS
 
Image Segmentation (HP)
100% 2680
43.4 IPS
 
Image Segmentation (Q)
98% 4441
72.2 IPS
 
Pose Estimation (SP)
100% 4995
5.83 IPS
 
Pose Estimation (HP)
100% 4739
5.53 IPS
 
Pose Estimation (Q)
84% 11067
13.1 IPS
 
Object Detection (SP)
98% 2424
192.9 IPS
 
Object Detection (HP)
98% 2449
194.9 IPS
 
Object Detection (Q)
87% 3763
302.2 IPS
 
Face Detection (SP)
100% 4364
51.9 IPS
 
Face Detection (HP)
100% 4366
51.9 IPS
 
Face Detection (Q)
95% 8290
99.0 IPS
 
Depth Estimation (SP)
98% 4554
35.2 IPS
 
Depth Estimation (HP)
99% 4617
35.7 IPS
 
Depth Estimation (Q)
75% 9479
76.9 IPS
 
Style Transfer (SP)
89% 11596
15.1 IPS
 
Style Transfer (HP)
89% 11459
14.9 IPS
 
Style Transfer (Q)
98% 23891
30.8 IPS
 
Image Super-Resolution (SP)
100% 2385
88.1 IPS
 
Image Super-Resolution (HP)
100% 2333
86.2 IPS
 
Image Super-Resolution (Q)
97% 5958
220.8 IPS
 
Text Classification (SP)
100% 1107
1.48 KIPS
 
Text Classification (HP)
99% 1109
1.48 KIPS
 
Text Classification (Q)
88% 1634
2.20 KIPS
 
Machine Translation (SP)
100% 1943
33.5 IPS
 
Machine Translation (HP)
100% 1831
31.5 IPS
 
Machine Translation (Q)
50% 933
33.1 IPS
 

Compare

Set Baseline Geekbench 6 now available