Geekbench AI Score

1053
Single Precision Score
1060
Half Precision Score
1992
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User iClondike
Upload Date January 28 2025 03:19 PM
Views 4

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 7.25 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 436
81.1 IPS
 
Image Classification (HP)
100% 470
87.4 IPS
 
Image Classification (Q)
100% 1455
270.6 IPS
 
Image Segmentation (SP)
100% 567
9.20 IPS
 
Image Segmentation (HP)
100% 549
8.90 IPS
 
Image Segmentation (Q)
98% 1618
26.3 IPS
 
Pose Estimation (SP)
100% 2086
2.43 IPS
 
Pose Estimation (HP)
100% 2139
2.50 IPS
 
Pose Estimation (Q)
84% 3649
4.33 IPS
 
Object Detection (SP)
100% 466
37.0 IPS
 
Object Detection (HP)
100% 465
36.9 IPS
 
Object Detection (Q)
83% 1311
105.9 IPS
 
Face Detection (SP)
100% 1514
18.0 IPS
 
Face Detection (HP)
100% 1520
18.1 IPS
 
Face Detection (Q)
95% 3188
38.1 IPS
 
Depth Estimation (SP)
100% 2083
16.0 IPS
 
Depth Estimation (HP)
99% 2108
16.2 IPS
 
Depth Estimation (Q)
64% 3289
30.1 IPS
 
Style Transfer (SP)
89% 4122
5.35 IPS
 
Style Transfer (HP)
89% 4110
5.34 IPS
 
Style Transfer (Q)
98% 8339
10.8 IPS
 
Image Super-Resolution (SP)
100% 1153
42.6 IPS
 
Image Super-Resolution (HP)
100% 1087
40.1 IPS
 
Image Super-Resolution (Q)
97% 1993
73.8 IPS
 
Text Classification (SP)
100% 568
758.2 IPS
 
Text Classification (HP)
100% 566
755.3 IPS
 
Text Classification (Q)
88% 1031
1.39 KIPS
 
Machine Translation (SP)
100% 827
14.3 IPS
 
Machine Translation (HP)
100% 865
14.9 IPS
 
Machine Translation (Q)
50% 488
17.3 IPS
 

Compare

Set Baseline Geekbench 6 now available