Geekbench AI Score

512
Single Precision Score
509
Half Precision Score
960
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User guinea7pig
Upload Date May 20 2025 06:35 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 730G
System Information
Operating System Android 13
Model Google Pixel 4a
Model IDGoogle Pixel 4a
Motherboard sunfish
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 13 part 2052 revision 14
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 5.47 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 230
42.7 IPS
 
Image Classification (HP)
100% 222
41.3 IPS
 
Image Classification (Q)
100% 655
121.8 IPS
 
Image Segmentation (SP)
100% 285
4.62 IPS
 
Image Segmentation (HP)
100% 283
4.59 IPS
 
Image Segmentation (Q)
98% 725
11.8 IPS
 
Pose Estimation (SP)
100% 1126
1.31 IPS
 
Pose Estimation (HP)
100% 1097
1.28 IPS
 
Pose Estimation (Q)
84% 1633
1.94 IPS
 
Object Detection (SP)
100% 230
18.2 IPS
 
Object Detection (HP)
100% 230
18.2 IPS
 
Object Detection (Q)
83% 657
53.0 IPS
 
Face Detection (SP)
100% 709
8.43 IPS
 
Face Detection (HP)
100% 708
8.42 IPS
 
Face Detection (Q)
95% 1506
18.0 IPS
 
Depth Estimation (SP)
100% 908
7.00 IPS
 
Depth Estimation (HP)
99% 932
7.18 IPS
 
Depth Estimation (Q)
64% 1516
13.9 IPS
 
Style Transfer (SP)
89% 1861
2.42 IPS
 
Style Transfer (HP)
89% 1861
2.42 IPS
 
Style Transfer (Q)
98% 3731
4.81 IPS
 
Image Super-Resolution (SP)
100% 493
18.2 IPS
 
Image Super-Resolution (HP)
100% 495
18.3 IPS
 
Image Super-Resolution (Q)
97% 923
34.2 IPS
 
Text Classification (SP)
100% 271
361.1 IPS
 
Text Classification (HP)
100% 269
358.7 IPS
 
Text Classification (Q)
88% 515
695.0 IPS
 
Machine Translation (SP)
100% 458
7.89 IPS
 
Machine Translation (HP)
100% 452
7.78 IPS
 
Machine Translation (Q)
50% 323
11.5 IPS
 

Compare

Set Baseline Geekbench 6 now available