Geekbench AI Score

2614
Single Precision Score
2696
Half Precision Score
3992
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 21 2024 04:44 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 8 Gen 3
System Information
Operating System Android 14
Model Samsung Galaxy S24+
Model IDsamsung SM-S926U1
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 @ 3.40 GHz
Memory Information
Size 10.83 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2478
460.8 IPS
 
Image Classification (HP)
100% 2487
462.4 IPS
 
Image Classification (Q)
100% 3195
594.2 IPS
 
Image Segmentation (SP)
100% 2761
44.8 IPS
 
Image Segmentation (HP)
100% 2753
44.6 IPS
 
Image Segmentation (Q)
98% 4253
69.2 IPS
 
Pose Estimation (SP)
100% 4231
4.94 IPS
 
Pose Estimation (HP)
100% 4144
4.84 IPS
 
Pose Estimation (Q)
84% 9945
11.8 IPS
 
Object Detection (SP)
98% 2121
168.8 IPS
 
Object Detection (HP)
98% 2190
174.3 IPS
 
Object Detection (Q)
83% 3420
276.2 IPS
 
Face Detection (SP)
100% 4246
50.4 IPS
 
Face Detection (HP)
100% 4240
50.4 IPS
 
Face Detection (Q)
95% 5736
68.5 IPS
 
Depth Estimation (SP)
99% 3341
25.8 IPS
 
Depth Estimation (HP)
99% 3784
29.2 IPS
 
Depth Estimation (Q)
64% 6487
59.4 IPS
 
Style Transfer (SP)
89% 9676
12.6 IPS
 
Style Transfer (HP)
89% 8785
11.4 IPS
 
Style Transfer (Q)
98% 16708
21.5 IPS
 
Image Super-Resolution (SP)
100% 1722
63.6 IPS
 
Image Super-Resolution (HP)
100% 1766
65.2 IPS
 
Image Super-Resolution (Q)
97% 4258
157.8 IPS
 
Text Classification (SP)
100% 725
967.7 IPS
 
Text Classification (HP)
99% 774
1.03 KIPS
 
Text Classification (Q)
88% 1176
1.59 KIPS
 
Machine Translation (SP)
100% 1420
24.5 IPS
 
Machine Translation (HP)
100% 1700
29.3 IPS
 
Machine Translation (Q)
50% 716
25.4 IPS
 

Compare

Set Baseline Geekbench 6 now available