Geekbench ML Score

1663
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date September 04 2025 02:41 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% 468
87.5 IPS
 
Image Classification (F16)
100% 1702
318.4 IPS
 
Image Classification (I8)
97% 4721
883.4 IPS
 
Image Segmentation (F32)
100% 586
9.79 IPS
 
Image Segmentation (F16)
100% 1797
30.0 IPS
 
Image Segmentation (I8)
98% 2135
35.7 IPS
 
Pose Estimation (F32)
100% 2878
3.49 IPS
 
Pose Estimation (F16)
100% 4824
5.84 IPS
 
Pose Estimation (I8)
100% 26744
32.4 IPS
 
Object Detection (F32)
100% 333
24.9 IPS
 
Object Detection (F16)
100% 1355
101.1 IPS
 
Object Detection (I8)
64% 1952
145.8 IPS
 
Face Detection (F32)
100% 1458
17.3 IPS
 
Face Detection (F16)
97% 4510
53.6 IPS
 
Face Detection (I8)
86% 9951
118.3 IPS
 
Depth Estimation (F32)
100% 419
3.25 IPS
 
Depth Estimation (F16)
100% 7553
58.6 IPS
 
Depth Estimation (I8)
95% 13887
107.7 IPS
 
Style Transfer (F32)
100% 1694
2.23 IPS
 
Style Transfer (F16)
100% 1586
2.09 IPS
 
Style Transfer (I8)
31% 4463
5.87 IPS
 
Image Super-Resolution (F32)
100% 1126
40.2 IPS
 
Image Super-Resolution (F16)
100% 4446
158.8 IPS
 
Image Super-Resolution (I8)
33% 9925
354.5 IPS
 
Text Classification (F32)
100% 68
97.2 IPS
 
Text Classification (F16)
100% 975
1.40 KIPS
 
Text Classification (I8)
92% 1200
1.72 KIPS
 
Machine Translation (F32)
100% 190
3.49 IPS
 
Machine Translation (F16)
100% 188
3.46 IPS
 
Machine Translation (I8)
66% 316
5.81 IPS
 

Compare

Set Baseline Geekbench 6 now available