Geekbench AI Score

341
Single Precision Score
2708
Half Precision Score
7432
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User tavcsor
Upload Date February 26 2025 09:06 AM
Views 5

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% 214
39.8 IPS
 
Image Classification (HP)
100% 5611
1.04 KIPS
 
Image Classification (Q)
99% 8634
1.61 KIPS
 
Image Segmentation (SP)
100% 276
4.48 IPS
 
Image Segmentation (HP)
100% 5372
87.1 IPS
 
Image Segmentation (Q)
98% 9441
153.5 IPS
 
Pose Estimation (SP)
100% 356
0.42 IPS
 
Pose Estimation (HP)
100% 20899
24.4 IPS
 
Pose Estimation (Q)
97% 37941
44.4 IPS
 
Object Detection (SP)
100% 207
16.4 IPS
 
Object Detection (HP)
100% 4668
370.2 IPS
 
Object Detection (Q)
87% 6589
528.6 IPS
 
Face Detection (SP)
100% 498
5.91 IPS
 
Face Detection (HP)
100% 498
5.92 IPS
 
Face Detection (Q)
97% 31472
375.3 IPS
 
Depth Estimation (SP)
100% 434
3.34 IPS
 
Depth Estimation (HP)
99% 22725
175.1 IPS
 
Depth Estimation (Q)
64% 33102
304.7 IPS
 
Style Transfer (SP)
100% 703
0.90 IPS
 
Style Transfer (HP)
100% 704
0.90 IPS
 
Style Transfer (Q)
58% 2322
4.17 IPS
 
Image Super-Resolution (SP)
100% 219
8.07 IPS
 
Image Super-Resolution (HP)
100% 6147
227.0 IPS
 
Image Super-Resolution (Q)
97% 13589
503.5 IPS
 
Text Classification (SP)
100% 315
420.9 IPS
 
Text Classification (HP)
100% 317
423.0 IPS
 
Text Classification (Q)
92% 2478
3.33 KIPS
 
Machine Translation (SP)
100% 472
8.13 IPS
 
Machine Translation (HP)
100% 465
8.00 IPS
 
Machine Translation (Q)
57% 310
7.58 IPS
 

Compare

Set Baseline Geekbench 6 now available