Geekbench AI Score

382
Single Precision Score
4638
Half Precision Score
9087
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User fridriksa
Upload Date March 08 2025 11:17 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% 281
52.3 IPS
 
Image Classification (HP)
100% 6032
1.12 KIPS
 
Image Classification (Q)
99% 8361
1.56 KIPS
 
Image Segmentation (SP)
100% 357
5.79 IPS
 
Image Segmentation (HP)
100% 8270
134.1 IPS
 
Image Segmentation (Q)
98% 18041
293.4 IPS
 
Pose Estimation (SP)
100% 452
0.53 IPS
 
Pose Estimation (HP)
100% 32377
37.8 IPS
 
Pose Estimation (Q)
97% 65510
76.7 IPS
 
Object Detection (SP)
100% 256
20.3 IPS
 
Object Detection (HP)
100% 5469
433.8 IPS
 
Object Detection (Q)
87% 7878
631.9 IPS
 
Face Detection (SP)
100% 642
7.62 IPS
 
Face Detection (HP)
100% 17482
207.7 IPS
 
Face Detection (Q)
97% 35782
426.6 IPS
 
Depth Estimation (SP)
100% 552
4.26 IPS
 
Depth Estimation (HP)
99% 36744
283.1 IPS
 
Depth Estimation (Q)
64% 45869
422.3 IPS
 
Style Transfer (SP)
100% 826
1.06 IPS
 
Style Transfer (HP)
100% 777
1.00 IPS
 
Style Transfer (Q)
72% 3050
4.19 IPS
 
Image Super-Resolution (SP)
100% 224
8.26 IPS
 
Image Super-Resolution (HP)
100% 10293
380.1 IPS
 
Image Super-Resolution (Q)
97% 19072
706.7 IPS
 
Text Classification (SP)
100% 200
267.1 IPS
 
Text Classification (HP)
100% 201
267.9 IPS
 
Text Classification (Q)
92% 2018
2.71 KIPS
 
Machine Translation (SP)
100% 436
7.51 IPS
 
Machine Translation (HP)
100% 505
8.70 IPS
 
Machine Translation (Q)
57% 256
6.25 IPS
 

Compare

Set Baseline Geekbench 6 now available