Geekbench AI Score

510
Single Precision Score
508
Half Precision Score
947
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 11 2024 02:51 AM
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% 224
41.7 IPS
 
Image Classification (HP)
100% 228
42.3 IPS
 
Image Classification (Q)
100% 639
118.8 IPS
 
Image Segmentation (SP)
100% 282
4.57 IPS
 
Image Segmentation (HP)
100% 283
4.58 IPS
 
Image Segmentation (Q)
98% 710
11.5 IPS
 
Pose Estimation (SP)
100% 1119
1.31 IPS
 
Pose Estimation (HP)
100% 1121
1.31 IPS
 
Pose Estimation (Q)
84% 1641
1.95 IPS
 
Object Detection (SP)
100% 229
18.2 IPS
 
Object Detection (HP)
100% 229
18.2 IPS
 
Object Detection (Q)
83% 646
52.2 IPS
 
Face Detection (SP)
100% 714
8.48 IPS
 
Face Detection (HP)
100% 717
8.52 IPS
 
Face Detection (Q)
95% 1478
17.6 IPS
 
Depth Estimation (SP)
100% 893
6.88 IPS
 
Depth Estimation (HP)
99% 833
6.42 IPS
 
Depth Estimation (Q)
64% 1511
13.8 IPS
 
Style Transfer (SP)
89% 1878
2.44 IPS
 
Style Transfer (HP)
89% 1891
2.45 IPS
 
Style Transfer (Q)
98% 3779
4.87 IPS
 
Image Super-Resolution (SP)
100% 474
17.5 IPS
 
Image Super-Resolution (HP)
100% 483
17.8 IPS
 
Image Super-Resolution (Q)
97% 919
34.1 IPS
 
Text Classification (SP)
100% 276
367.9 IPS
 
Text Classification (HP)
100% 274
365.1 IPS
 
Text Classification (Q)
88% 483
651.8 IPS
 
Machine Translation (SP)
100% 472
8.13 IPS
 
Machine Translation (HP)
100% 470
8.10 IPS
 
Machine Translation (Q)
50% 324
11.5 IPS
 

Compare

Set Baseline Geekbench 6 now available