Geekbench AI Score

430
Single Precision Score
5063
Half Precision Score
6607
Quantized Score
Geekbench AI 1.0.0 for Android AArch64

Result Information

User hass
Upload Date September 05 2024 02:56 PM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM ARMv8
System Information
Operating System Android 14
Model Google Pixel 9 Pro
Model IDGoogle Pixel 9 Pro
Motherboard caiman
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% 279
51.8 IPS
 
Image Classification (HP)
100% 5471
1.02 KIPS
 
Image Classification (Q)
99% 5729
1.07 KIPS
 
Image Segmentation (SP)
100% 348
5.64 IPS
 
Image Segmentation (HP)
100% 9794
158.8 IPS
 
Image Segmentation (Q)
98% 20933
340.4 IPS
 
Pose Estimation (SP)
100% 430
0.50 IPS
 
Pose Estimation (HP)
100% 31822
37.1 IPS
 
Pose Estimation (Q)
97% 63824
74.7 IPS
 
Object Detection (SP)
100% 248
19.7 IPS
 
Object Detection (HP)
100% 5512
437.2 IPS
 
Object Detection (Q)
90% 7022
561.4 IPS
 
Face Detection (SP)
100% 623
7.40 IPS
 
Face Detection (HP)
100% 16284
193.5 IPS
 
Face Detection (Q)
97% 33696
401.8 IPS
 
Depth Estimation (SP)
100% 542
4.18 IPS
 
Depth Estimation (HP)
99% 34326
264.5 IPS
 
Depth Estimation (Q)
70% 40322
339.7 IPS
 
Style Transfer (SP)
100% 809
1.04 IPS
 
Style Transfer (HP)
100% 803
1.03 IPS
 
Style Transfer (Q)
27% 225
4.65 IPS
 
Image Super-Resolution (SP)
100% 295
10.9 IPS
 
Image Super-Resolution (HP)
100% 10246
378.4 IPS
 
Image Super-Resolution (Q)
97% 19428
719.9 IPS
 
Text Classification (SP)
100% 421
561.4 IPS
 
Text Classification (HP)
100% 425
567.1 IPS
 
Text Classification (Q)
92% 1161
1.56 KIPS
 
Machine Translation (SP)
100% 616
10.6 IPS
 
Machine Translation (HP)
100% 603
10.4 IPS
 
Machine Translation (Q)
57% 428
10.5 IPS
 

Compare

Set Baseline Geekbench 6 now available