Geekbench AI Score

273
Single Precision Score
275
Half Precision Score
432
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User DoomSlayer
Upload Date November 09 2024 05:40 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM Qualcomm
System Information
Operating System Android 14
Model Xiaomi M2012K11AI
Model IDXiaomi M2012K11AI
Motherboard kona
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 3.19 GHz
Memory Information
Size 5.50 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 173
32.1 IPS
 
Image Classification (HP)
100% 174
32.3 IPS
 
Image Classification (Q)
96% 1307
244.1 IPS
 
Image Segmentation (SP)
100% 221
3.58 IPS
 
Image Segmentation (HP)
100% 223
3.62 IPS
 
Image Segmentation (Q)
98% 1233
20.1 IPS
 
Pose Estimation (SP)
100% 290
0.34 IPS
 
Pose Estimation (HP)
100% 290
0.34 IPS
 
Pose Estimation (Q)
96% 13265
15.5 IPS
 
Object Detection (SP)
100% 169
13.4 IPS
 
Object Detection (HP)
100% 171
13.5 IPS
 
Object Detection (Q)
84% 1264
102.0 IPS
 
Face Detection (SP)
100% 401
4.76 IPS
 
Face Detection (HP)
100% 407
4.83 IPS
 
Face Detection (Q)
97% 2150
25.6 IPS
 
Depth Estimation (SP)
100% 337
2.59 IPS
 
Depth Estimation (HP)
99% 338
2.60 IPS
 
Depth Estimation (Q)
0% 0
50.6 IPS
 
Style Transfer (SP)
100% 546
0.70 IPS
 
Style Transfer (HP)
100% 549
0.71 IPS
 
Style Transfer (Q)
98% 18717
24.1 IPS
 
Image Super-Resolution (SP)
100% 167
6.16 IPS
 
Image Super-Resolution (HP)
100% 167
6.17 IPS
 
Image Super-Resolution (Q)
97% 666
24.7 IPS
 
Text Classification (SP)
100% 257
343.0 IPS
 
Text Classification (HP)
100% 258
343.8 IPS
 
Text Classification (Q)
93% 315
422.4 IPS
 
Machine Translation (SP)
100% 399
6.87 IPS
 
Machine Translation (HP)
100% 401
6.91 IPS
 
Machine Translation (Q)
0% 0
2.07 IPS
 

Compare

Set Baseline Geekbench 6 now available