Geekbench AI Score

364
Single Precision Score
3960
Half Precision Score
6595
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User JiggaBoom
Upload Date February 26 2025 09:35 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device Google Tensor G3
System Information
Operating System Android 15
Model Google Pixel 8 Pro
Model IDGoogle Pixel 8 Pro
Motherboard husky
Governorsched_pixel
CPU Information
Name ARM ARMv8
Topology 1 Processor, 9 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 1.70 GHz
Cluster 14 Cores @ 1.70 GHz
Cluster 24 Cores @ 2.37 GHz
Cluster 31 Core @ 2.91 GHz
Memory Information
Size 11.32 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 272
50.6 IPS
 
Image Classification (HP)
100% 3350
623.0 IPS
 
Image Classification (Q)
99% 4728
881.9 IPS
 
Image Segmentation (SP)
100% 356
5.77 IPS
 
Image Segmentation (HP)
100% 8012
129.9 IPS
 
Image Segmentation (Q)
98% 14252
231.7 IPS
 
Pose Estimation (SP)
100% 422
0.49 IPS
 
Pose Estimation (HP)
100% 31009
36.2 IPS
 
Pose Estimation (Q)
97% 62408
73.1 IPS
 
Object Detection (SP)
100% 228
18.1 IPS
 
Object Detection (HP)
100% 4017
318.6 IPS
 
Object Detection (Q)
87% 4915
394.3 IPS
 
Face Detection (SP)
100% 544
6.47 IPS
 
Face Detection (HP)
100% 13432
159.6 IPS
 
Face Detection (Q)
97% 27249
324.9 IPS
 
Depth Estimation (SP)
100% 446
3.43 IPS
 
Depth Estimation (HP)
99% 30689
236.4 IPS
 
Depth Estimation (Q)
64% 31579
290.7 IPS
 
Style Transfer (SP)
100% 640
0.82 IPS
 
Style Transfer (HP)
100% 656
0.84 IPS
 
Style Transfer (Q)
73% 2644
3.63 IPS
 
Image Super-Resolution (SP)
100% 237
8.76 IPS
 
Image Super-Resolution (HP)
100% 7916
292.3 IPS
 
Image Super-Resolution (Q)
97% 13248
490.9 IPS
 
Text Classification (SP)
100% 295
393.8 IPS
 
Text Classification (HP)
100% 296
394.8 IPS
 
Text Classification (Q)
92% 944
1.27 KIPS
 
Machine Translation (SP)
100% 413
7.11 IPS
 
Machine Translation (HP)
100% 448
7.72 IPS
 
Machine Translation (Q)
57% 265
6.48 IPS
 

Compare

Set Baseline Geekbench 6 now available