Geekbench ML Score

1653
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date September 04 2025 04:38 AM
Views 8

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% 467
87.5 IPS
 
Image Classification (F16)
100% 1690
316.2 IPS
 
Image Classification (I8)
97% 4696
878.7 IPS
 
Image Segmentation (F32)
100% 588
9.83 IPS
 
Image Segmentation (F16)
100% 1805
30.1 IPS
 
Image Segmentation (I8)
98% 2135
35.7 IPS
 
Pose Estimation (F32)
100% 2877
3.48 IPS
 
Pose Estimation (F16)
100% 4774
5.78 IPS
 
Pose Estimation (I8)
100% 26882
32.6 IPS
 
Object Detection (F32)
100% 335
25.0 IPS
 
Object Detection (F16)
100% 1235
92.2 IPS
 
Object Detection (I8)
64% 1959
146.2 IPS
 
Face Detection (F32)
100% 1460
17.4 IPS
 
Face Detection (F16)
97% 4512
53.7 IPS
 
Face Detection (I8)
86% 9872
117.4 IPS
 
Depth Estimation (F32)
100% 420
3.25 IPS
 
Depth Estimation (F16)
100% 7602
59.0 IPS
 
Depth Estimation (I8)
95% 12637
98.0 IPS
 
Style Transfer (F32)
100% 1695
2.23 IPS
 
Style Transfer (F16)
100% 1582
2.08 IPS
 
Style Transfer (I8)
31% 4471
5.88 IPS
 
Image Super-Resolution (F32)
100% 1118
39.9 IPS
 
Image Super-Resolution (F16)
100% 4439
158.5 IPS
 
Image Super-Resolution (I8)
33% 10336
369.1 IPS
 
Text Classification (F32)
100% 67
96.4 IPS
 
Text Classification (F16)
100% 973
1.40 KIPS
 
Text Classification (I8)
92% 1198
1.72 KIPS
 
Machine Translation (F32)
100% 190
3.50 IPS
 
Machine Translation (F16)
100% 187
3.44 IPS
 
Machine Translation (I8)
66% 317
5.84 IPS
 

Compare

Set Baseline Geekbench 6 now available