Geekbench AI Score

394
Single Precision Score
4600
Half Precision Score
9359
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User fridriksa
Upload Date April 03 2025 01:16 PM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device Google Tensor G4
System Information
Operating System Android 15
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
51.9 IPS
 
Image Classification (HP)
100% 6340
1.18 KIPS
 
Image Classification (Q)
99% 8349
1.56 KIPS
 
Image Segmentation (SP)
100% 354
5.74 IPS
 
Image Segmentation (HP)
100% 8122
131.7 IPS
 
Image Segmentation (Q)
98% 17288
281.1 IPS
 
Pose Estimation (SP)
100% 443
0.52 IPS
 
Pose Estimation (HP)
100% 32068
37.4 IPS
 
Pose Estimation (Q)
97% 65286
76.5 IPS
 
Object Detection (SP)
100% 255
20.3 IPS
 
Object Detection (HP)
100% 5533
438.9 IPS
 
Object Detection (Q)
87% 7802
625.8 IPS
 
Face Detection (SP)
100% 634
7.53 IPS
 
Face Detection (HP)
100% 17055
202.6 IPS
 
Face Detection (Q)
97% 34894
416.1 IPS
 
Depth Estimation (SP)
100% 548
4.22 IPS
 
Depth Estimation (HP)
99% 34896
268.9 IPS
 
Depth Estimation (Q)
64% 41809
384.9 IPS
 
Style Transfer (SP)
100% 825
1.06 IPS
 
Style Transfer (HP)
100% 810
1.04 IPS
 
Style Transfer (Q)
72% 3294
4.53 IPS
 
Image Super-Resolution (SP)
100% 275
10.2 IPS
 
Image Super-Resolution (HP)
100% 10354
382.3 IPS
 
Image Super-Resolution (Q)
97% 19290
714.8 IPS
 
Text Classification (SP)
100% 212
282.5 IPS
 
Text Classification (HP)
100% 212
282.5 IPS
 
Text Classification (Q)
92% 2294
3.08 KIPS
 
Machine Translation (SP)
100% 493
8.50 IPS
 
Machine Translation (HP)
100% 439
7.55 IPS
 
Machine Translation (Q)
57% 330
8.07 IPS
 

Compare

Set Baseline Geekbench 6 now available