Geekbench ML Score

1656
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date September 04 2025 01:21 AM
Views 2

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% 1717
321.3 IPS
 
Image Classification (I8)
97% 4729
884.9 IPS
 
Image Segmentation (F32)
100% 591
9.86 IPS
 
Image Segmentation (F16)
100% 1808
30.2 IPS
 
Image Segmentation (I8)
98% 2143
35.8 IPS
 
Pose Estimation (F32)
100% 2876
3.48 IPS
 
Pose Estimation (F16)
100% 4826
5.84 IPS
 
Pose Estimation (I8)
100% 26842
32.5 IPS
 
Object Detection (F32)
100% 336
25.1 IPS
 
Object Detection (F16)
100% 1115
83.2 IPS
 
Object Detection (I8)
64% 1951
145.6 IPS
 
Face Detection (F32)
100% 1471
17.5 IPS
 
Face Detection (F16)
97% 4652
55.3 IPS
 
Face Detection (I8)
86% 10083
119.9 IPS
 
Depth Estimation (F32)
100% 422
3.27 IPS
 
Depth Estimation (F16)
100% 7615
59.1 IPS
 
Depth Estimation (I8)
95% 13606
105.5 IPS
 
Style Transfer (F32)
100% 1697
2.23 IPS
 
Style Transfer (F16)
100% 1588
2.09 IPS
 
Style Transfer (I8)
31% 4453
5.86 IPS
 
Image Super-Resolution (F32)
100% 1125
40.2 IPS
 
Image Super-Resolution (F16)
100% 4453
159.0 IPS
 
Image Super-Resolution (I8)
33% 10257
366.3 IPS
 
Text Classification (F32)
100% 67
96.5 IPS
 
Text Classification (F16)
100% 968
1.39 KIPS
 
Text Classification (I8)
92% 1197
1.72 KIPS
 
Machine Translation (F32)
100% 189
3.49 IPS
 
Machine Translation (F16)
100% 187
3.44 IPS
 
Machine Translation (I8)
66% 310
5.71 IPS
 

Compare

Set Baseline Geekbench 6 now available