Geekbench AI Score

257
Single Precision Score
11757
Half Precision Score
29368
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 19 2024 01:40 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM ARMv8
System Information
Operating System Android 14
Model Xiaomi 24030PN60G
Model IDXiaomi 24030PN60G
Motherboard aurora
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 @ 3.30 GHz
Memory Information
Size 14.86 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 153
28.4 IPS
 
Image Classification (HP)
100% 12136
2.26 KIPS
 
Image Classification (Q)
97% 30963
5.78 KIPS
 
Image Segmentation (SP)
100% 204
3.30 IPS
 
Image Segmentation (HP)
100% 8801
142.7 IPS
 
Image Segmentation (Q)
98% 23487
381.9 IPS
 
Pose Estimation (SP)
100% 264
0.31 IPS
 
Pose Estimation (HP)
100% 62043
72.4 IPS
 
Pose Estimation (Q)
98% 322593
377.6 IPS
 
Object Detection (SP)
100% 144
11.4 IPS
 
Object Detection (HP)
100% 11226
890.4 IPS
 
Object Detection (Q)
86% 13359
1.07 KIPS
 
Face Detection (SP)
100% 426
5.07 IPS
 
Face Detection (HP)
100% 25002
297.1 IPS
 
Face Detection (Q)
97% 85319
1.02 KIPS
 
Depth Estimation (SP)
100% 344
2.65 IPS
 
Depth Estimation (HP)
99% 44639
343.9 IPS
 
Depth Estimation (Q)
63% 89267
835.9 IPS
 
Style Transfer (SP)
100% 614
0.79 IPS
 
Style Transfer (HP)
24% 2710
82.0 IPS
 
Style Transfer (Q)
98% 221918
286.2 IPS
 
Image Super-Resolution (SP)
100% 164
6.05 IPS
 
Image Super-Resolution (HP)
100% 30674
1.13 KIPS
 
Image Super-Resolution (Q)
97% 80524
2.98 KIPS
 
Text Classification (SP)
100% 199
265.0 IPS
 
Text Classification (HP)
100% 2473
3.30 KIPS
 
Text Classification (Q)
93% 5254
7.05 KIPS
 
Machine Translation (SP)
100% 361
6.21 IPS
 
Machine Translation (HP)
100% 2958
50.9 IPS
 
Machine Translation (Q)
30% 213
42.7 IPS
 

Compare

Set Baseline Geekbench 6 now available