Geekbench AI Score

445
Single Precision Score
439
Half Precision Score
814
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 06 2025 02:53 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM MT6781V/CDZAMB-H
System Information
Operating System Android 13
Model realme RMX3151
Model IDrealme RMX3151
Motherboard RM6781
CPU Information
Name ARM MT6781V/CDZAMB-H
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.05 GHz
Memory Information
Size 3.63 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 211
39.2 IPS
 
Image Classification (HP)
100% 203
37.8 IPS
 
Image Classification (Q)
100% 621
115.4 IPS
 
Image Segmentation (SP)
100% 264
4.27 IPS
 
Image Segmentation (HP)
100% 257
4.16 IPS
 
Image Segmentation (Q)
98% 677
11.0 IPS
 
Pose Estimation (SP)
100% 985
1.15 IPS
 
Pose Estimation (HP)
100% 940
1.10 IPS
 
Pose Estimation (Q)
84% 1394
1.65 IPS
 
Object Detection (SP)
100% 194
15.4 IPS
 
Object Detection (HP)
100% 193
15.3 IPS
 
Object Detection (Q)
83% 561
45.3 IPS
 
Face Detection (SP)
100% 640
7.60 IPS
 
Face Detection (HP)
100% 642
7.63 IPS
 
Face Detection (Q)
95% 1273
15.2 IPS
 
Depth Estimation (SP)
100% 833
6.42 IPS
 
Depth Estimation (HP)
99% 815
6.28 IPS
 
Depth Estimation (Q)
64% 1286
11.8 IPS
 
Style Transfer (SP)
89% 1547
2.01 IPS
 
Style Transfer (HP)
89% 1586
2.06 IPS
 
Style Transfer (Q)
98% 3014
3.89 IPS
 
Image Super-Resolution (SP)
100% 410
15.2 IPS
 
Image Super-Resolution (HP)
100% 410
15.1 IPS
 
Image Super-Resolution (Q)
97% 732
27.1 IPS
 
Text Classification (SP)
100% 217
290.1 IPS
 
Text Classification (HP)
100% 216
288.7 IPS
 
Text Classification (Q)
88% 396
533.9 IPS
 
Machine Translation (SP)
100% 393
6.77 IPS
 
Machine Translation (HP)
100% 390
6.71 IPS
 
Machine Translation (Q)
50% 274
9.73 IPS
 

Compare

Set Baseline Geekbench 6 now available