Geekbench AI Score

512
Single Precision Score
508
Half Precision Score
942
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 06 2025 04:29 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
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 7.46 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 228
42.3 IPS
 
Image Classification (HP)
100% 225
41.9 IPS
 
Image Classification (Q)
100% 635
118.1 IPS
 
Image Segmentation (SP)
100% 284
4.60 IPS
 
Image Segmentation (HP)
100% 284
4.61 IPS
 
Image Segmentation (Q)
98% 711
11.6 IPS
 
Pose Estimation (SP)
100% 1117
1.30 IPS
 
Pose Estimation (HP)
100% 1105
1.29 IPS
 
Pose Estimation (Q)
84% 1635
1.94 IPS
 
Object Detection (SP)
100% 228
18.1 IPS
 
Object Detection (HP)
100% 229
18.1 IPS
 
Object Detection (Q)
83% 648
52.3 IPS
 
Face Detection (SP)
100% 716
8.51 IPS
 
Face Detection (HP)
100% 715
8.50 IPS
 
Face Detection (Q)
95% 1466
17.5 IPS
 
Depth Estimation (SP)
100% 916
7.05 IPS
 
Depth Estimation (HP)
99% 892
6.87 IPS
 
Depth Estimation (Q)
64% 1496
13.7 IPS
 
Style Transfer (SP)
89% 1862
2.42 IPS
 
Style Transfer (HP)
89% 1871
2.43 IPS
 
Style Transfer (Q)
98% 3755
4.84 IPS
 
Image Super-Resolution (SP)
100% 477
17.6 IPS
 
Image Super-Resolution (HP)
100% 475
17.6 IPS
 
Image Super-Resolution (Q)
97% 917
34.0 IPS
 
Text Classification (SP)
100% 273
365.0 IPS
 
Text Classification (HP)
100% 270
359.9 IPS
 
Text Classification (Q)
88% 469
632.3 IPS
 
Machine Translation (SP)
100% 473
8.15 IPS
 
Machine Translation (HP)
100% 466
8.03 IPS
 
Machine Translation (Q)
50% 325
11.6 IPS
 

Compare

Set Baseline Geekbench 6 now available