Geekbench AI Score

2881
Single Precision Score
2880
Half Precision Score
4517
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User oldnick
Upload Date January 15 2025 03:40 PM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model LENOVO TB321FU
Model IDLENOVO TB321FU
Motherboard pineapple
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.26 GHz
Cluster 12 Cores @ 2.27 GHz
Cluster 22 Cores @ 2.96 GHz
Cluster 33 Cores @ 3.15 GHz
Cluster 41 Core @ 3.30 GHz
Memory Information
Size 11.01 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2086
388.0 IPS
 
Image Classification (HP)
100% 2441
454.0 IPS
 
Image Classification (Q)
100% 3418
635.6 IPS
 
Image Segmentation (SP)
100% 2656
43.1 IPS
 
Image Segmentation (HP)
100% 2692
43.6 IPS
 
Image Segmentation (Q)
98% 4132
67.2 IPS
 
Pose Estimation (SP)
100% 4113
4.80 IPS
 
Pose Estimation (HP)
100% 3996
4.66 IPS
 
Pose Estimation (Q)
84% 9682
11.5 IPS
 
Object Detection (SP)
98% 2202
175.2 IPS
 
Object Detection (HP)
98% 2071
164.8 IPS
 
Object Detection (Q)
83% 3100
250.4 IPS
 
Face Detection (SP)
100% 4202
49.9 IPS
 
Face Detection (HP)
100% 4278
50.8 IPS
 
Face Detection (Q)
95% 7580
90.5 IPS
 
Depth Estimation (SP)
99% 4242
32.8 IPS
 
Depth Estimation (HP)
99% 4202
32.5 IPS
 
Depth Estimation (Q)
64% 6951
63.7 IPS
 
Style Transfer (SP)
89% 10249
13.3 IPS
 
Style Transfer (HP)
89% 9974
12.9 IPS
 
Style Transfer (Q)
98% 19811
25.5 IPS
 
Image Super-Resolution (SP)
100% 2202
81.3 IPS
 
Image Super-Resolution (HP)
100% 2183
80.6 IPS
 
Image Super-Resolution (Q)
97% 5424
201.0 IPS
 
Text Classification (SP)
100% 1056
1.41 KIPS
 
Text Classification (HP)
99% 1055
1.41 KIPS
 
Text Classification (Q)
88% 1527
2.06 KIPS
 
Machine Translation (SP)
100% 1854
31.9 IPS
 
Machine Translation (HP)
100% 1754
30.2 IPS
 
Machine Translation (Q)
50% 966
34.3 IPS
 

Compare

Set Baseline Geekbench 6 now available