Geekbench ML Score

1654
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date September 03 2025 09:22 AM
Views 1

System Information

System Information
Operating System Android 14
Model alps tb8775p1_64_titan_whitesnake_25b
Model IDalps tb8775p1_64_titan_whitesnake_25b
Motherboard tb8775p1_64_titan_whitesnake_25b
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 24 Cores @ 2.50 GHz
Memory Information
Size 5.16 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 465
87.1 IPS
 
Image Classification (F16)
100% 1702
318.4 IPS
 
Image Classification (I8)
97% 4760
890.7 IPS
 
Image Segmentation (F32)
100% 588
9.83 IPS
 
Image Segmentation (F16)
100% 1799
30.0 IPS
 
Image Segmentation (I8)
98% 2134
35.6 IPS
 
Pose Estimation (F32)
100% 2877
3.48 IPS
 
Pose Estimation (F16)
100% 4943
5.99 IPS
 
Pose Estimation (I8)
100% 26762
32.4 IPS
 
Object Detection (F32)
100% 335
25.0 IPS
 
Object Detection (F16)
100% 1048
78.2 IPS
 
Object Detection (I8)
64% 1951
145.7 IPS
 
Face Detection (F32)
100% 1464
17.4 IPS
 
Face Detection (F16)
97% 4515
53.7 IPS
 
Face Detection (I8)
86% 9953
118.3 IPS
 
Depth Estimation (F32)
100% 419
3.25 IPS
 
Depth Estimation (F16)
100% 7560
58.6 IPS
 
Depth Estimation (I8)
95% 14289
110.8 IPS
 
Style Transfer (F32)
100% 1696
2.23 IPS
 
Style Transfer (F16)
100% 1590
2.09 IPS
 
Style Transfer (I8)
31% 4465
5.87 IPS
 
Image Super-Resolution (F32)
100% 1126
40.2 IPS
 
Image Super-Resolution (F16)
100% 4431
158.3 IPS
 
Image Super-Resolution (I8)
33% 10330
368.9 IPS
 
Text Classification (F32)
100% 67
96.8 IPS
 
Text Classification (F16)
100% 980
1.41 KIPS
 
Text Classification (I8)
92% 1204
1.73 KIPS
 
Machine Translation (F32)
100% 190
3.50 IPS
 
Machine Translation (F16)
100% 187
3.45 IPS
 
Machine Translation (I8)
66% 318
5.85 IPS
 

Compare

Set Baseline Geekbench 6 now available