Geekbench AI Score

574
Single Precision Score
865
Half Precision Score
653
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 19 2025 12:21 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device placeholder
System Information
Operating System Android 13
Model Google brya
Model IDGoogle brya
Motherboard omnigul
CPU Information
Name placeholder
Topology 1 Processor, 8 Cores
Identifier ARM implementer 78 architecture 8 variant 2 part 0 revision 1
Base Frequency 0 MHz
Cluster 18 Cores
Memory Information
Size 6.83 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 469
87.2 IPS
 
Image Classification (HP)
100% 700
130.1 IPS
 
Image Classification (Q)
96% 664
124.0 IPS
 
Image Segmentation (SP)
100% 568
9.21 IPS
 
Image Segmentation (HP)
100% 915
14.8 IPS
 
Image Segmentation (Q)
98% 679
11.0 IPS
 
Pose Estimation (SP)
100% 797
0.93 IPS
 
Pose Estimation (HP)
100% 1476
1.72 IPS
 
Pose Estimation (Q)
94% 1432
1.68 IPS
 
Object Detection (SP)
100% 375
29.7 IPS
 
Object Detection (HP)
100% 564
44.8 IPS
 
Object Detection (Q)
86% 556
44.7 IPS
 
Face Detection (SP)
100% 1243
14.8 IPS
 
Face Detection (HP)
100% 1994
23.7 IPS
 
Face Detection (Q)
96% 1585
18.9 IPS
 
Depth Estimation (SP)
100% 975
7.51 IPS
 
Depth Estimation (HP)
99% 1700
13.1 IPS
 
Depth Estimation (Q)
63% 1387
12.9 IPS
 
Style Transfer (SP)
100% 2517
3.24 IPS
 
Style Transfer (HP)
100% 4601
5.92 IPS
 
Style Transfer (Q)
98% 4443
5.73 IPS
 
Image Super-Resolution (SP)
100% 490
18.1 IPS
 
Image Super-Resolution (HP)
100% 867
32.0 IPS
 
Image Super-Resolution (Q)
97% 790
29.3 IPS
 
Text Classification (SP)
100% 134
178.3 IPS
 
Text Classification (HP)
100% 133
177.5 IPS
 
Text Classification (Q)
91% 65
87.4 IPS
 
Machine Translation (SP)
100% 245
4.22 IPS
 
Machine Translation (HP)
100% 245
4.21 IPS
 
Machine Translation (Q)
57% 79
1.94 IPS
 

Compare

Set Baseline Geekbench 6 now available