Geekbench AI Score

519
Single Precision Score
615
Half Precision Score
604
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User aeonsim
Upload Date September 08 2024 08:45 AM
Views 5

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device Google Tensor G2
System Information
Operating System Android 14
Model Google Pixel 7
Model IDGoogle Pixel 7
Motherboard panther
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 7.30 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 242
45.0 IPS
 
Image Classification (HP)
100% 246
45.8 IPS
 
Image Classification (Q)
99% 256
47.8 IPS
 
Image Segmentation (SP)
100% 649
10.5 IPS
 
Image Segmentation (HP)
100% 819
13.3 IPS
 
Image Segmentation (Q)
98% 821
13.3 IPS
 
Pose Estimation (SP)
100% 453
0.53 IPS
 
Pose Estimation (HP)
100% 622
0.73 IPS
 
Pose Estimation (Q)
96% 618
0.72 IPS
 
Object Detection (SP)
100% 216
17.1 IPS
 
Object Detection (HP)
100% 291
23.1 IPS
 
Object Detection (Q)
83% 289
23.4 IPS
 
Face Detection (SP)
100% 1065
12.7 IPS
 
Face Detection (HP)
100% 1310
15.6 IPS
 
Face Detection (Q)
97% 1203
14.3 IPS
 
Depth Estimation (SP)
100% 758
5.84 IPS
 
Depth Estimation (HP)
99% 915
7.05 IPS
 
Depth Estimation (Q)
62% 736
6.97 IPS
 
Style Transfer (SP)
100% 2005
2.58 IPS
 
Style Transfer (HP)
100% 2574
3.31 IPS
 
Style Transfer (Q)
98% 2560
3.30 IPS
 
Image Super-Resolution (SP)
100% 358
13.2 IPS
 
Image Super-Resolution (HP)
100% 445
16.5 IPS
 
Image Super-Resolution (Q)
97% 449
16.6 IPS
 
Text Classification (SP)
100% 327
437.0 IPS
 
Text Classification (HP)
100% 327
437.1 IPS
 
Text Classification (Q)
91% 537
722.4 IPS
 
Machine Translation (SP)
100% 487
8.38 IPS
 
Machine Translation (HP)
100% 475
8.17 IPS
 
Machine Translation (Q)
57% 316
7.73 IPS
 

Compare

Set Baseline Geekbench 6 now available