Geekbench AI Score

2023
Single Precision Score
2046
Half Precision Score
3106
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Mckbrian
Upload Date February 14 2025 02:02 AM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Google Tensor G4
System Information
Operating System Android 15
Model Google Pixel 9 Pro XL
Model IDGoogle Pixel 9 Pro XL
Motherboard komodo
Governorsched_pixel
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 1.95 GHz
Cluster 14 Cores @ 1.95 GHz
Cluster 23 Cores @ 2.60 GHz
Cluster 31 Core @ 3.10 GHz
Memory Information
Size 15.19 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1396
259.6 IPS
 
Image Classification (HP)
100% 1563
290.7 IPS
 
Image Classification (Q)
100% 2301
427.9 IPS
 
Image Segmentation (SP)
100% 1732
28.1 IPS
 
Image Segmentation (HP)
100% 1715
27.8 IPS
 
Image Segmentation (Q)
98% 2404
39.1 IPS
 
Pose Estimation (SP)
100% 3013
3.52 IPS
 
Pose Estimation (HP)
100% 2955
3.45 IPS
 
Pose Estimation (Q)
84% 6479
7.68 IPS
 
Object Detection (SP)
98% 1417
112.8 IPS
 
Object Detection (HP)
98% 1423
113.2 IPS
 
Object Detection (Q)
83% 2237
180.7 IPS
 
Face Detection (SP)
100% 2985
35.5 IPS
 
Face Detection (HP)
100% 2975
35.3 IPS
 
Face Detection (Q)
95% 4610
55.0 IPS
 
Depth Estimation (SP)
99% 3194
24.7 IPS
 
Depth Estimation (HP)
99% 3172
24.5 IPS
 
Depth Estimation (Q)
64% 4930
45.2 IPS
 
Style Transfer (SP)
89% 7161
9.30 IPS
 
Style Transfer (HP)
89% 7105
9.22 IPS
 
Style Transfer (Q)
98% 13868
17.9 IPS
 
Image Super-Resolution (SP)
100% 1577
58.2 IPS
 
Image Super-Resolution (HP)
100% 1628
60.1 IPS
 
Image Super-Resolution (Q)
97% 3498
129.6 IPS
 
Text Classification (SP)
100% 685
913.7 IPS
 
Text Classification (HP)
99% 731
975.6 IPS
 
Text Classification (Q)
88% 1288
1.74 KIPS
 
Machine Translation (SP)
100% 1513
26.1 IPS
 
Machine Translation (HP)
100% 1431
24.7 IPS
 
Machine Translation (Q)
50% 736
26.1 IPS
 

Compare

Set Baseline Geekbench 6 now available