Geekbench AI Score

1109
Single Precision Score
1097
Half Precision Score
1999
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User HimenoSena
Upload Date February 01 2025 02:45 PM
Views 6

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device HiSilicon Kirin 990
System Information
Operating System Android 12
Model Huawei Honor V30 Pro
Model IDHUAWEI OXF-AN10
Motherboard OXF
CPU Information
Name ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 72 architecture 8 variant 3 part 3392 revision 1
Base Frequency 1.95 GHz
Cluster 14 Cores @ 1.95 GHz
Cluster 22 Cores @ 2.36 GHz
Cluster 32 Cores @ 2.86 GHz
Memory Information
Size 7.33 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 528
98.2 IPS
 
Image Classification (HP)
100% 529
98.5 IPS
 
Image Classification (Q)
100% 1400
260.4 IPS
 
Image Segmentation (SP)
100% 635
10.3 IPS
 
Image Segmentation (HP)
100% 629
10.2 IPS
 
Image Segmentation (Q)
98% 1517
24.7 IPS
 
Pose Estimation (SP)
100% 2347
2.74 IPS
 
Pose Estimation (HP)
100% 2360
2.75 IPS
 
Pose Estimation (Q)
84% 3658
4.34 IPS
 
Object Detection (SP)
100% 510
40.5 IPS
 
Object Detection (HP)
100% 515
40.9 IPS
 
Object Detection (Q)
83% 1397
112.8 IPS
 
Face Detection (SP)
100% 1545
18.4 IPS
 
Face Detection (HP)
100% 1544
18.4 IPS
 
Face Detection (Q)
95% 3208
38.3 IPS
 
Depth Estimation (SP)
100% 2002
15.4 IPS
 
Depth Estimation (HP)
99% 2009
15.5 IPS
 
Depth Estimation (Q)
64% 3310
30.3 IPS
 
Style Transfer (SP)
89% 3869
5.02 IPS
 
Style Transfer (HP)
89% 3860
5.01 IPS
 
Style Transfer (Q)
98% 8334
10.7 IPS
 
Image Super-Resolution (SP)
100% 1126
41.6 IPS
 
Image Super-Resolution (HP)
100% 955
35.3 IPS
 
Image Super-Resolution (Q)
97% 1962
72.7 IPS
 
Text Classification (SP)
100% 577
769.6 IPS
 
Text Classification (HP)
100% 594
792.4 IPS
 
Text Classification (Q)
88% 988
1.33 KIPS
 
Machine Translation (SP)
100% 907
15.6 IPS
 
Machine Translation (HP)
100% 924
15.9 IPS
 
Machine Translation (Q)
50% 550
19.5 IPS
 

Compare

Set Baseline Geekbench 6 now available