Geekbench AI Score

489
Single Precision Score
12176
Half Precision Score
36203
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 18 2024 02:19 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM ARMv8
System Information
Operating System Android 14
Model Xiaomi 23127PN0CG
Model IDXiaomi 23127PN0CG
Motherboard houji
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 10.94 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 310
57.6 IPS
 
Image Classification (HP)
100% 12346
2.30 KIPS
 
Image Classification (Q)
97% 36289
6.77 KIPS
 
Image Segmentation (SP)
100% 386
6.25 IPS
 
Image Segmentation (HP)
100% 8513
138.0 IPS
 
Image Segmentation (Q)
98% 29248
475.6 IPS
 
Pose Estimation (SP)
100% 501
0.58 IPS
 
Pose Estimation (HP)
100% 60421
70.5 IPS
 
Pose Estimation (Q)
98% 277423
324.7 IPS
 
Object Detection (SP)
100% 296
23.4 IPS
 
Object Detection (HP)
100% 11098
880.3 IPS
 
Object Detection (Q)
86% 19243
1.55 KIPS
 
Face Detection (SP)
100% 720
8.55 IPS
 
Face Detection (HP)
100% 33502
398.1 IPS
 
Face Detection (Q)
97% 126580
1.51 KIPS
 
Depth Estimation (SP)
100% 615
4.74 IPS
 
Depth Estimation (HP)
99% 42822
329.9 IPS
 
Depth Estimation (Q)
63% 96476
903.4 IPS
 
Style Transfer (SP)
100% 984
1.27 IPS
 
Style Transfer (HP)
24% 2684
81.2 IPS
 
Style Transfer (Q)
98% 296108
381.8 IPS
 
Image Super-Resolution (SP)
100% 334
12.3 IPS
 
Image Super-Resolution (HP)
100% 29339
1.08 KIPS
 
Image Super-Resolution (Q)
97% 96574
3.58 KIPS
 
Text Classification (SP)
100% 443
591.1 IPS
 
Text Classification (HP)
100% 3222
4.30 KIPS
 
Text Classification (Q)
93% 6788
9.11 KIPS
 
Machine Translation (SP)
100% 685
11.8 IPS
 
Machine Translation (HP)
100% 2792
48.1 IPS
 
Machine Translation (Q)
30% 288
57.8 IPS
 

Compare

Set Baseline Geekbench 6 now available