Geekbench AI Score

913
Single Precision Score
1328
Half Precision Score
1246
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Annihilator
Upload Date January 01 2025 11:12 AM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 14
Model HONOR PGT-N19
Model IDHONOR PGT-N19
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.19 GHz
Memory Information
Size 10.87 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 582
108.2 IPS
 
Image Classification (HP)
100% 1055
196.2 IPS
 
Image Classification (Q)
96% 1046
195.3 IPS
 
Image Segmentation (SP)
100% 1258
20.4 IPS
 
Image Segmentation (HP)
100% 1978
32.1 IPS
 
Image Segmentation (Q)
98% 1062
17.3 IPS
 
Pose Estimation (SP)
100% 953
1.11 IPS
 
Pose Estimation (HP)
100% 1422
1.66 IPS
 
Pose Estimation (Q)
96% 1417
1.66 IPS
 
Object Detection (SP)
100% 465
36.9 IPS
 
Object Detection (HP)
100% 742
58.9 IPS
 
Object Detection (Q)
87% 799
64.2 IPS
 
Face Detection (SP)
100% 2084
24.8 IPS
 
Face Detection (HP)
100% 3295
39.2 IPS
 
Face Detection (Q)
97% 3078
36.7 IPS
 
Depth Estimation (SP)
100% 1411
10.9 IPS
 
Depth Estimation (HP)
99% 2704
20.9 IPS
 
Depth Estimation (Q)
63% 2210
20.5 IPS
 
Style Transfer (SP)
100% 3622
4.66 IPS
 
Style Transfer (HP)
100% 8149
10.5 IPS
 
Style Transfer (Q)
98% 7995
10.3 IPS
 
Image Super-Resolution (SP)
100% 434
16.0 IPS
 
Image Super-Resolution (HP)
100% 397
14.7 IPS
 
Image Super-Resolution (Q)
97% 384
14.2 IPS
 
Text Classification (SP)
100% 428
571.7 IPS
 
Text Classification (HP)
100% 432
576.7 IPS
 
Text Classification (Q)
91% 683
917.5 IPS
 
Machine Translation (SP)
100% 627
10.8 IPS
 
Machine Translation (HP)
100% 624
10.8 IPS
 
Machine Translation (Q)
57% 503
12.3 IPS
 

Compare

Set Baseline Geekbench 6 now available