Geekbench ML Score

1648
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date September 04 2025 04:47 AM
Views 3

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% 466
87.3 IPS
 
Image Classification (F16)
100% 1706
319.3 IPS
 
Image Classification (I8)
97% 4746
888.1 IPS
 
Image Segmentation (F32)
100% 590
9.86 IPS
 
Image Segmentation (F16)
100% 1802
30.1 IPS
 
Image Segmentation (I8)
98% 2149
35.9 IPS
 
Pose Estimation (F32)
100% 2879
3.49 IPS
 
Pose Estimation (F16)
100% 4852
5.88 IPS
 
Pose Estimation (I8)
100% 26765
32.4 IPS
 
Object Detection (F32)
100% 334
25.0 IPS
 
Object Detection (F16)
100% 1118
83.4 IPS
 
Object Detection (I8)
64% 1944
145.2 IPS
 
Face Detection (F32)
100% 1465
17.4 IPS
 
Face Detection (F16)
97% 4516
53.7 IPS
 
Face Detection (I8)
86% 9921
118.0 IPS
 
Depth Estimation (F32)
100% 419
3.25 IPS
 
Depth Estimation (F16)
100% 7605
59.0 IPS
 
Depth Estimation (I8)
95% 13154
102.0 IPS
 
Style Transfer (F32)
100% 1697
2.23 IPS
 
Style Transfer (F16)
100% 1590
2.09 IPS
 
Style Transfer (I8)
31% 4468
5.88 IPS
 
Image Super-Resolution (F32)
100% 1121
40.0 IPS
 
Image Super-Resolution (F16)
100% 4426
158.0 IPS
 
Image Super-Resolution (I8)
33% 9478
338.5 IPS
 
Text Classification (F32)
100% 67
96.8 IPS
 
Text Classification (F16)
100% 985
1.42 KIPS
 
Text Classification (I8)
92% 1196
1.72 KIPS
 
Machine Translation (F32)
100% 190
3.50 IPS
 
Machine Translation (F16)
100% 188
3.45 IPS
 
Machine Translation (I8)
66% 317
5.83 IPS
 

Compare

Set Baseline Geekbench 6 now available