Geekbench AI Score

336
Single Precision Score
2647
Half Precision Score
7369
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User yasin9300
Upload Date December 22 2024 10:14 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device Google Tensor G2
System Information
Operating System Android 15
Model Google Pixel Tablet
Model IDGoogle Pixel Tablet
Motherboard tangorpro
Governorsched_pixel
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.35 GHz
Cluster 32 Cores @ 2.85 GHz
Memory Information
Size 7.27 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 208
38.7 IPS
 
Image Classification (HP)
100% 5430
1.01 KIPS
 
Image Classification (Q)
99% 8577
1.60 KIPS
 
Image Segmentation (SP)
100% 265
4.29 IPS
 
Image Segmentation (HP)
100% 5054
81.9 IPS
 
Image Segmentation (Q)
98% 9379
152.5 IPS
 
Pose Estimation (SP)
100% 351
0.41 IPS
 
Pose Estimation (HP)
100% 20835
24.3 IPS
 
Pose Estimation (Q)
97% 37886
44.4 IPS
 
Object Detection (SP)
100% 203
16.1 IPS
 
Object Detection (HP)
100% 4408
349.7 IPS
 
Object Detection (Q)
87% 6417
514.8 IPS
 
Face Detection (SP)
100% 487
5.79 IPS
 
Face Detection (HP)
100% 484
5.75 IPS
 
Face Detection (Q)
97% 31656
377.4 IPS
 
Depth Estimation (SP)
100% 432
3.33 IPS
 
Depth Estimation (HP)
99% 21778
167.8 IPS
 
Depth Estimation (Q)
64% 32328
297.6 IPS
 
Style Transfer (SP)
100% 698
0.90 IPS
 
Style Transfer (HP)
100% 704
0.91 IPS
 
Style Transfer (Q)
58% 2299
4.13 IPS
 
Image Super-Resolution (SP)
100% 221
8.15 IPS
 
Image Super-Resolution (HP)
100% 6165
227.6 IPS
 
Image Super-Resolution (Q)
97% 13607
504.2 IPS
 
Text Classification (SP)
100% 315
420.8 IPS
 
Text Classification (HP)
100% 315
419.8 IPS
 
Text Classification (Q)
92% 2451
3.29 KIPS
 
Machine Translation (SP)
100% 467
8.05 IPS
 
Machine Translation (HP)
100% 465
8.01 IPS
 
Machine Translation (Q)
57% 308
7.52 IPS
 

Compare

Set Baseline Geekbench 6 now available