Geekbench AI Score

760
Single Precision Score
753
Half Precision Score
1607
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Nimazh
Upload Date December 25 2024 07:13 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model Xiaomi 2306EPN60G
Model IDXiaomi 2306EPN60G
Motherboard aristotle
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 23 Cores @ 3.00 GHz
Cluster 31 Core @ 3.10 GHz
Memory Information
Size 11.17 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 470
87.3 IPS
 
Image Classification (HP)
100% 468
87.1 IPS
 
Image Classification (Q)
100% 1349
250.9 IPS
 
Image Segmentation (SP)
100% 603
9.78 IPS
 
Image Segmentation (HP)
100% 604
9.79 IPS
 
Image Segmentation (Q)
98% 1540
25.0 IPS
 
Pose Estimation (SP)
100% 1930
2.25 IPS
 
Pose Estimation (HP)
100% 1413
1.65 IPS
 
Pose Estimation (Q)
84% 2929
3.47 IPS
 
Object Detection (SP)
100% 366
29.1 IPS
 
Object Detection (HP)
100% 359
28.5 IPS
 
Object Detection (Q)
83% 961
77.6 IPS
 
Face Detection (SP)
100% 1177
14.0 IPS
 
Face Detection (HP)
100% 1035
12.3 IPS
 
Face Detection (Q)
95% 2387
28.5 IPS
 
Depth Estimation (SP)
100% 913
7.03 IPS
 
Depth Estimation (HP)
99% 1554
12.0 IPS
 
Depth Estimation (Q)
64% 2619
24.0 IPS
 
Style Transfer (SP)
89% 2619
3.40 IPS
 
Style Transfer (HP)
89% 2316
3.01 IPS
 
Style Transfer (Q)
98% 6715
8.66 IPS
 
Image Super-Resolution (SP)
100% 457
16.9 IPS
 
Image Super-Resolution (HP)
100% 447
16.5 IPS
 
Image Super-Resolution (Q)
97% 1608
59.6 IPS
 
Text Classification (SP)
100% 453
604.7 IPS
 
Text Classification (HP)
100% 451
602.2 IPS
 
Text Classification (Q)
88% 837
1.13 KIPS
 
Machine Translation (SP)
100% 556
9.57 IPS
 
Machine Translation (HP)
100% 547
9.43 IPS
 
Machine Translation (Q)
50% 349
12.4 IPS
 

Compare

Set Baseline Geekbench 6 now available