Geekbench AI Score

2054
Single Precision Score
1997
Half Precision Score
3121
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User epicgeek
Upload Date February 04 2025 11:07 PM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model samsung SM-S931B
Model IDsamsung SM-S931B
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 1 revision 4
Base Frequency 3.53 GHz
Cluster 16 Cores @ 3.53 GHz
Cluster 22 Cores @ 4.47 GHz
Memory Information
Size 10.86 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2016
374.9 IPS
 
Image Classification (HP)
100% 1958
364.1 IPS
 
Image Classification (Q)
100% 4358
810.5 IPS
 
Image Segmentation (SP)
100% 2409
39.0 IPS
 
Image Segmentation (HP)
100% 1147
18.6 IPS
 
Image Segmentation (Q)
98% 1311
21.3 IPS
 
Pose Estimation (SP)
100% 2726
3.18 IPS
 
Pose Estimation (HP)
100% 4371
5.10 IPS
 
Pose Estimation (Q)
84% 8736
10.4 IPS
 
Object Detection (SP)
98% 966
76.9 IPS
 
Object Detection (HP)
98% 805
64.1 IPS
 
Object Detection (Q)
83% 2696
217.8 IPS
 
Face Detection (SP)
100% 3223
38.3 IPS
 
Face Detection (HP)
100% 3493
41.5 IPS
 
Face Detection (Q)
95% 6626
79.1 IPS
 
Depth Estimation (SP)
99% 3258
25.2 IPS
 
Depth Estimation (HP)
99% 4133
31.9 IPS
 
Depth Estimation (Q)
64% 8442
77.3 IPS
 
Style Transfer (SP)
89% 9158
11.9 IPS
 
Style Transfer (HP)
89% 7529
9.77 IPS
 
Style Transfer (Q)
98% 14312
18.5 IPS
 
Image Super-Resolution (SP)
100% 1458
53.8 IPS
 
Image Super-Resolution (HP)
100% 1665
61.5 IPS
 
Image Super-Resolution (Q)
97% 3601
133.4 IPS
 
Text Classification (SP)
100% 550
733.9 IPS
 
Text Classification (HP)
99% 550
734.2 IPS
 
Text Classification (Q)
88% 661
892.1 IPS
 
Machine Translation (SP)
100% 1361
23.5 IPS
 
Machine Translation (HP)
100% 1285
22.1 IPS
 
Machine Translation (Q)
50% 342
12.1 IPS
 

Compare

Set Baseline Geekbench 6 now available