Geekbench AI Score

2065
Single Precision Score
3195
Half Precision Score
2431
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User xgrommx
Upload Date October 16 2025 12:07 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 15
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 14.92 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1299
241.5 IPS
 
Image Classification (HP)
100% 1872
348.1 IPS
 
Image Classification (Q)
100% 1635
304.1 IPS
 
Image Segmentation (SP)
100% 2652
43.0 IPS
 
Image Segmentation (HP)
100% 4488
72.7 IPS
 
Image Segmentation (Q)
98% 3760
61.1 IPS
 
Pose Estimation (SP)
100% 10303
12.0 IPS
 
Pose Estimation (HP)
99% 18694
21.9 IPS
 
Pose Estimation (Q)
96% 18284
21.4 IPS
 
Object Detection (SP)
100% 1138
90.2 IPS
 
Object Detection (HP)
99% 1719
136.3 IPS
 
Object Detection (Q)
87% 1635
131.3 IPS
 
Face Detection (SP)
100% 4214
50.1 IPS
 
Face Detection (HP)
100% 7310
86.9 IPS
 
Face Detection (Q)
97% 5549
66.2 IPS
 
Depth Estimation (SP)
100% 5353
41.2 IPS
 
Depth Estimation (HP)
98% 7816
60.4 IPS
 
Depth Estimation (Q)
61% 5976
58.9 IPS
 
Style Transfer (SP)
100% 12991
16.7 IPS
 
Style Transfer (HP)
100% 26979
34.7 IPS
 
Style Transfer (Q)
98% 27038
34.9 IPS
 
Image Super-Resolution (SP)
100% 2843
105.0 IPS
 
Image Super-Resolution (HP)
100% 4487
165.7 IPS
 
Image Super-Resolution (Q)
97% 4295
159.2 IPS
 
Text Classification (SP)
35% 49
475.2 IPS
 
Text Classification (HP)
35% 66
601.4 IPS
 
Text Classification (Q)
33% 46
556.1 IPS
 
Machine Translation (SP)
100% 856
14.8 IPS
 
Machine Translation (HP)
97% 900
15.6 IPS
 
Machine Translation (Q)
43% 222
12.6 IPS
 

Compare

Set Baseline Geekbench 6 now available