Geekbench AI Score

2016
Single Precision Score
2035
Half Precision Score
3094
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User sebeg_the_tea_boii
Upload Date October 25 2024 03:48 PM
Views 7

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
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% 1340
249.1 IPS
 
Image Classification (HP)
100% 1529
284.4 IPS
 
Image Classification (Q)
100% 2446
454.9 IPS
 
Image Segmentation (SP)
100% 1646
26.7 IPS
 
Image Segmentation (HP)
100% 1653
26.8 IPS
 
Image Segmentation (Q)
98% 2387
38.8 IPS
 
Pose Estimation (SP)
100% 2992
3.49 IPS
 
Pose Estimation (HP)
100% 2899
3.38 IPS
 
Pose Estimation (Q)
84% 6489
7.70 IPS
 
Object Detection (SP)
98% 1542
122.7 IPS
 
Object Detection (HP)
98% 1564
124.5 IPS
 
Object Detection (Q)
83% 2138
172.7 IPS
 
Face Detection (SP)
100% 2968
35.3 IPS
 
Face Detection (HP)
100% 3047
36.2 IPS
 
Face Detection (Q)
95% 4900
58.5 IPS
 
Depth Estimation (SP)
99% 3105
24.0 IPS
 
Depth Estimation (HP)
99% 3008
23.2 IPS
 
Depth Estimation (Q)
64% 5061
46.4 IPS
 
Style Transfer (SP)
89% 7137
9.27 IPS
 
Style Transfer (HP)
89% 7041
9.14 IPS
 
Style Transfer (Q)
98% 13758
17.7 IPS
 
Image Super-Resolution (SP)
100% 1577
58.2 IPS
 
Image Super-Resolution (HP)
100% 1580
58.3 IPS
 
Image Super-Resolution (Q)
97% 3539
131.1 IPS
 
Text Classification (SP)
100% 663
884.9 IPS
 
Text Classification (HP)
99% 679
905.7 IPS
 
Text Classification (Q)
88% 1105
1.49 KIPS
 
Machine Translation (SP)
100% 1589
27.4 IPS
 
Machine Translation (HP)
100% 1541
26.5 IPS
 
Machine Translation (Q)
50% 746
26.5 IPS
 

Compare

Set Baseline Geekbench 6 now available