Geekbench ML Score

635
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date January 06 2024 08:29 PM
Views 1

System Information

System Information
Operating System Android 14
Model Google Pixel 6 Pro
Model IDGoogle Pixel 6 Pro
Motherboard raven
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 @ 2.25 GHz
Cluster 32 Cores @ 2.80 GHz
Memory Information
Size 11.28 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 293
54.8 IPS
 
Image Classification (F16)
100% 454
85.0 IPS
 
Image Classification (I8)
97% 423
79.1 IPS
 
Image Segmentation (F32)
100% 632
10.6 IPS
 
Image Segmentation (F16)
100% 1016
17.0 IPS
 
Image Segmentation (I8)
98% 940
15.7 IPS
 
Pose Estimation (F32)
100% 327
0.40 IPS
 
Pose Estimation (F16)
100% 425
0.51 IPS
 
Pose Estimation (I8)
100% 423
0.51 IPS
 
Object Detection (F32)
100% 300
22.4 IPS
 
Object Detection (F16)
100% 427
31.9 IPS
 
Object Detection (I8)
62% 339
25.3 IPS
 
Face Detection (F32)
100% 1522
18.1 IPS
 
Face Detection (F16)
98% 1927
22.9 IPS
 
Face Detection (I8)
86% 1923
22.9 IPS
 
Depth Estimation (F32)
100% 652
5.06 IPS
 
Depth Estimation (F16)
100% 722
5.60 IPS
 
Depth Estimation (I8)
95% 773
6.00 IPS
 
Style Transfer (F32)
100% 1373
1.81 IPS
 
Style Transfer (F16)
100% 2532
3.33 IPS
 
Style Transfer (I8)
98% 2534
3.33 IPS
 
Image Super-Resolution (F32)
100% 432
15.4 IPS
 
Image Super-Resolution (F16)
100% 665
23.8 IPS
 
Image Super-Resolution (I8)
98% 657
23.5 IPS
 
Text Classification (F32)
100% 294
422.6 IPS
 
Text Classification (F16)
100% 292
419.9 IPS
 
Text Classification (I8)
92% 505
725.9 IPS
 
Machine Translation (F32)
100% 466
8.57 IPS
 
Machine Translation (F16)
100% 460
8.46 IPS
 
Machine Translation (I8)
64% 459
8.45 IPS
 

Compare

Set Baseline Geekbench 6 now available