Geekbench AI Score

255
Single Precision Score
260
Half Precision Score
566
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 19 2024 02:10 AM
Views 5

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
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% 154
28.7 IPS
 
Image Classification (HP)
100% 154
28.7 IPS
 
Image Classification (Q)
99% 385
71.7 IPS
 
Image Segmentation (SP)
100% 205
3.32 IPS
 
Image Segmentation (HP)
100% 205
3.33 IPS
 
Image Segmentation (Q)
98% 408
6.63 IPS
 
Pose Estimation (SP)
100% 258
0.30 IPS
 
Pose Estimation (HP)
100% 251
0.29 IPS
 
Pose Estimation (Q)
98% 959
1.12 IPS
 
Object Detection (SP)
100% 144
11.4 IPS
 
Object Detection (HP)
100% 144
11.4 IPS
 
Object Detection (Q)
87% 397
31.8 IPS
 
Face Detection (SP)
100% 427
5.07 IPS
 
Face Detection (HP)
100% 428
5.09 IPS
 
Face Detection (Q)
97% 822
9.80 IPS
 
Depth Estimation (SP)
100% 341
2.63 IPS
 
Depth Estimation (HP)
99% 341
2.62 IPS
 
Depth Estimation (Q)
64% 776
7.04 IPS
 
Style Transfer (SP)
100% 613
0.79 IPS
 
Style Transfer (HP)
100% 735
0.94 IPS
 
Style Transfer (Q)
98% 1699
2.19 IPS
 
Image Super-Resolution (SP)
100% 163
6.01 IPS
 
Image Super-Resolution (HP)
100% 164
6.05 IPS
 
Image Super-Resolution (Q)
97% 555
20.6 IPS
 
Text Classification (SP)
100% 199
265.9 IPS
 
Text Classification (HP)
100% 200
267.4 IPS
 
Text Classification (Q)
91% 325
436.6 IPS
 
Machine Translation (SP)
100% 356
6.13 IPS
 
Machine Translation (HP)
100% 356
6.13 IPS
 
Machine Translation (Q)
57% 293
7.17 IPS
 

Compare

Set Baseline Geekbench 6 now available