Geekbench AI Score

263
Single Precision Score
19800
Half Precision Score
47532
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 22 2024 02:11 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM ARMv8
System Information
Operating System Android 15
Model realme RMX3888
Model IDrealme RMX3888
Motherboard pineapple
Governoruag
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 14.90 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 146
27.1 IPS
 
Image Classification (HP)
100% 14853
2.76 KIPS
 
Image Classification (Q)
97% 34858
6.51 KIPS
 
Image Segmentation (SP)
100% 195
3.16 IPS
 
Image Segmentation (HP)
100% 10229
165.8 IPS
 
Image Segmentation (Q)
98% 29136
473.8 IPS
 
Pose Estimation (SP)
100% 261
0.30 IPS
 
Pose Estimation (HP)
100% 75386
88.0 IPS
 
Pose Estimation (Q)
98% 393419
460.5 IPS
 
Object Detection (SP)
100% 144
11.4 IPS
 
Object Detection (HP)
100% 13579
1.08 KIPS
 
Object Detection (Q)
86% 18421
1.48 KIPS
 
Face Detection (SP)
100% 431
5.12 IPS
 
Face Detection (HP)
100% 29606
351.8 IPS
 
Face Detection (Q)
97% 102118
1.22 KIPS
 
Depth Estimation (SP)
100% 342
2.63 IPS
 
Depth Estimation (HP)
99% 57159
440.4 IPS
 
Depth Estimation (Q)
63% 111157
1.04 KIPS
 
Style Transfer (SP)
100% 609
0.78 IPS
 
Style Transfer (HP)
98% 81543
105.1 IPS
 
Style Transfer (Q)
98% 418408
539.5 IPS
 
Image Super-Resolution (SP)
100% 239
8.81 IPS
 
Image Super-Resolution (HP)
100% 39118
1.44 KIPS
 
Image Super-Resolution (Q)
97% 103398
3.83 KIPS
 
Text Classification (SP)
100% 198
263.7 IPS
 
Text Classification (HP)
100% 3187
4.25 KIPS
 
Text Classification (Q)
93% 6700
8.99 KIPS
 
Machine Translation (SP)
100% 357
6.15 IPS
 
Machine Translation (HP)
100% 3462
59.6 IPS
 
Machine Translation (Q)
55% 2431
63.7 IPS
 

Compare

Set Baseline Geekbench 6 now available