Geekbench AI Score

749
Single Precision Score
898
Half Precision Score
869
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 21 2025 05:18 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device Google Tensor G4
System Information
Operating System Android 16
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% 457
84.9 IPS
 
Image Classification (HP)
100% 455
84.5 IPS
 
Image Classification (Q)
99% 453
84.6 IPS
 
Image Segmentation (SP)
100% 795
12.9 IPS
 
Image Segmentation (HP)
100% 1238
20.1 IPS
 
Image Segmentation (Q)
98% 1019
16.6 IPS
 
Pose Estimation (SP)
100% 530
0.62 IPS
 
Pose Estimation (HP)
100% 740
0.86 IPS
 
Pose Estimation (Q)
96% 735
0.86 IPS
 
Object Detection (SP)
100% 410
32.6 IPS
 
Object Detection (HP)
100% 548
43.5 IPS
 
Object Detection (Q)
83% 558
45.1 IPS
 
Face Detection (SP)
100% 1811
21.5 IPS
 
Face Detection (HP)
100% 2135
25.4 IPS
 
Face Detection (Q)
97% 2144
25.6 IPS
 
Depth Estimation (SP)
100% 1012
7.79 IPS
 
Depth Estimation (HP)
99% 1255
9.67 IPS
 
Depth Estimation (Q)
62% 1017
9.62 IPS
 
Style Transfer (SP)
100% 2769
3.56 IPS
 
Style Transfer (HP)
100% 3608
4.64 IPS
 
Style Transfer (Q)
98% 3563
4.60 IPS
 
Image Super-Resolution (SP)
100% 587
21.7 IPS
 
Image Super-Resolution (HP)
100% 679
25.1 IPS
 
Image Super-Resolution (Q)
97% 650
24.1 IPS
 
Text Classification (SP)
100% 409
546.5 IPS
 
Text Classification (HP)
100% 406
542.4 IPS
 
Text Classification (Q)
91% 695
933.7 IPS
 
Machine Translation (SP)
100% 578
9.96 IPS
 
Machine Translation (HP)
100% 564
9.71 IPS
 
Machine Translation (Q)
57% 371
9.05 IPS
 

Compare

Set Baseline Geekbench 6 now available