Geekbench ML Score

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

Result Information

Upload Date September 04 2025 05:12 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% 467
87.3 IPS
 
Image Classification (F16)
100% 1700
318.0 IPS
 
Image Classification (I8)
97% 4676
874.9 IPS
 
Image Segmentation (F32)
100% 589
9.84 IPS
 
Image Segmentation (F16)
100% 1796
30.0 IPS
 
Image Segmentation (I8)
98% 2132
35.6 IPS
 
Pose Estimation (F32)
100% 2878
3.49 IPS
 
Pose Estimation (F16)
100% 5001
6.06 IPS
 
Pose Estimation (I8)
100% 26760
32.4 IPS
 
Object Detection (F32)
100% 334
24.9 IPS
 
Object Detection (F16)
100% 1115
83.3 IPS
 
Object Detection (I8)
64% 1940
144.9 IPS
 
Face Detection (F32)
100% 1468
17.5 IPS
 
Face Detection (F16)
97% 4518
53.7 IPS
 
Face Detection (I8)
86% 10029
119.3 IPS
 
Depth Estimation (F32)
100% 420
3.26 IPS
 
Depth Estimation (F16)
100% 7588
58.8 IPS
 
Depth Estimation (I8)
95% 13188
102.3 IPS
 
Style Transfer (F32)
100% 1696
2.23 IPS
 
Style Transfer (F16)
100% 1587
2.09 IPS
 
Style Transfer (I8)
31% 4462
5.87 IPS
 
Image Super-Resolution (F32)
100% 1123
40.1 IPS
 
Image Super-Resolution (F16)
100% 4434
158.3 IPS
 
Image Super-Resolution (I8)
33% 10347
369.5 IPS
 
Text Classification (F32)
100% 68
97.2 IPS
 
Text Classification (F16)
100% 973
1.40 KIPS
 
Text Classification (I8)
92% 1203
1.73 KIPS
 
Machine Translation (F32)
100% 190
3.50 IPS
 
Machine Translation (F16)
100% 188
3.45 IPS
 
Machine Translation (I8)
66% 316
5.82 IPS
 

Compare

Set Baseline Geekbench 6 now available