Geekbench AI Score

501
Single Precision Score
497
Half Precision Score
900
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date April 23 2025 05:59 AM
Views 1

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 7.45 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 226
42.1 IPS
 
Image Classification (HP)
100% 227
42.2 IPS
 
Image Classification (Q)
100% 630
117.1 IPS
 
Image Segmentation (SP)
100% 283
4.59 IPS
 
Image Segmentation (HP)
100% 283
4.59 IPS
 
Image Segmentation (Q)
98% 708
11.5 IPS
 
Pose Estimation (SP)
100% 1130
1.32 IPS
 
Pose Estimation (HP)
100% 1068
1.25 IPS
 
Pose Estimation (Q)
84% 1560
1.85 IPS
 
Object Detection (SP)
100% 221
17.5 IPS
 
Object Detection (HP)
100% 221
17.5 IPS
 
Object Detection (Q)
83% 617
49.8 IPS
 
Face Detection (SP)
100% 699
8.30 IPS
 
Face Detection (HP)
100% 701
8.33 IPS
 
Face Detection (Q)
95% 1399
16.7 IPS
 
Depth Estimation (SP)
100% 882
6.80 IPS
 
Depth Estimation (HP)
99% 867
6.68 IPS
 
Depth Estimation (Q)
64% 1431
13.1 IPS
 
Style Transfer (SP)
89% 1811
2.35 IPS
 
Style Transfer (HP)
89% 1812
2.35 IPS
 
Style Transfer (Q)
98% 3596
4.64 IPS
 
Image Super-Resolution (SP)
100% 474
17.5 IPS
 
Image Super-Resolution (HP)
100% 472
17.4 IPS
 
Image Super-Resolution (Q)
97% 867
32.1 IPS
 
Text Classification (SP)
100% 260
346.7 IPS
 
Text Classification (HP)
100% 258
343.8 IPS
 
Text Classification (Q)
88% 444
598.3 IPS
 
Machine Translation (SP)
100% 457
7.87 IPS
 
Machine Translation (HP)
100% 454
7.83 IPS
 
Machine Translation (Q)
50% 296
10.5 IPS
 

Compare

Set Baseline Geekbench 6 now available