Geekbench AI Score

511
Single Precision Score
508
Half Precision Score
926
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date August 17 2025 02:44 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 15
Model realme RMX3785
Model IDrealme RMX3785
Motherboard k6835v1_64
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.20 GHz
Memory Information
Size 7.44 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 225
41.8 IPS
 
Image Classification (HP)
100% 225
41.8 IPS
 
Image Classification (Q)
100% 636
118.4 IPS
 
Image Segmentation (SP)
100% 283
4.59 IPS
 
Image Segmentation (HP)
100% 281
4.56 IPS
 
Image Segmentation (Q)
98% 701
11.4 IPS
 
Pose Estimation (SP)
100% 1123
1.31 IPS
 
Pose Estimation (HP)
100% 1116
1.30 IPS
 
Pose Estimation (Q)
84% 1632
1.94 IPS
 
Object Detection (SP)
100% 227
18.0 IPS
 
Object Detection (HP)
100% 228
18.1 IPS
 
Object Detection (Q)
83% 637
51.5 IPS
 
Face Detection (SP)
100% 708
8.41 IPS
 
Face Detection (HP)
100% 702
8.34 IPS
 
Face Detection (Q)
95% 1452
17.3 IPS
 
Depth Estimation (SP)
100% 939
7.23 IPS
 
Depth Estimation (HP)
99% 912
7.02 IPS
 
Depth Estimation (Q)
64% 1486
13.6 IPS
 
Style Transfer (SP)
89% 1862
2.42 IPS
 
Style Transfer (HP)
89% 1870
2.43 IPS
 
Style Transfer (Q)
98% 3743
4.83 IPS
 
Image Super-Resolution (SP)
100% 481
17.8 IPS
 
Image Super-Resolution (HP)
100% 477
17.6 IPS
 
Image Super-Resolution (Q)
97% 904
33.5 IPS
 
Text Classification (SP)
100% 268
358.1 IPS
 
Text Classification (HP)
100% 267
355.8 IPS
 
Text Classification (Q)
88% 457
616.8 IPS
 
Machine Translation (SP)
100% 470
8.10 IPS
 
Machine Translation (HP)
100% 467
8.05 IPS
 
Machine Translation (Q)
50% 303
10.8 IPS
 

Compare

Set Baseline Geekbench 6 now available