Geekbench AI Score

441
Single Precision Score
435
Half Precision Score
766
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User kasid
Upload Date September 03 2025 10:26 PM
Views 9

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% 225
41.8 IPS
 
Image Classification (HP)
100% 225
41.9 IPS
 
Image Classification (Q)
100% 648
120.6 IPS
 
Image Segmentation (SP)
100% 249
4.04 IPS
 
Image Segmentation (HP)
100% 237
3.83 IPS
 
Image Segmentation (Q)
98% 578
9.39 IPS
 
Pose Estimation (SP)
100% 948
1.11 IPS
 
Pose Estimation (HP)
100% 942
1.10 IPS
 
Pose Estimation (Q)
84% 1234
1.46 IPS
 
Object Detection (SP)
100% 188
14.9 IPS
 
Object Detection (HP)
100% 188
14.9 IPS
 
Object Detection (Q)
83% 525
42.4 IPS
 
Face Detection (SP)
100% 623
7.41 IPS
 
Face Detection (HP)
100% 622
7.39 IPS
 
Face Detection (Q)
95% 1188
14.2 IPS
 
Depth Estimation (SP)
100% 823
6.34 IPS
 
Depth Estimation (HP)
99% 801
6.17 IPS
 
Depth Estimation (Q)
64% 1168
10.7 IPS
 
Style Transfer (SP)
89% 1507
1.96 IPS
 
Style Transfer (HP)
89% 1505
1.95 IPS
 
Style Transfer (Q)
98% 2873
3.71 IPS
 
Image Super-Resolution (SP)
100% 436
16.1 IPS
 
Image Super-Resolution (HP)
100% 437
16.1 IPS
 
Image Super-Resolution (Q)
97% 715
26.5 IPS
 
Text Classification (SP)
100% 214
285.1 IPS
 
Text Classification (HP)
100% 208
277.6 IPS
 
Text Classification (Q)
88% 367
494.9 IPS
 
Machine Translation (SP)
100% 387
6.66 IPS
 
Machine Translation (HP)
100% 382
6.57 IPS
 
Machine Translation (Q)
50% 276
9.79 IPS
 

Compare

Set Baseline Geekbench 6 now available