Geekbench AI Score

295
Single Precision Score
302
Half Precision Score
296
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 14 2025 01:05 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Samsung Exynos 850
System Information
Operating System Android 12
Model Samsung Galaxy A21s
Model IDsamsung SM-A217F
Motherboard exynos850
Governorenergy_step
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3333 revision 1
Base Frequency 2.00 GHz
Cluster 18 Cores @ 2.00 GHz
Memory Information
Size 2.64 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 132
24.5 IPS
 
Image Classification (HP)
100% 132
24.6 IPS
 
Image Classification (Q)
100% 189
35.2 IPS
 
Image Segmentation (SP)
100% 186
3.02 IPS
 
Image Segmentation (HP)
100% 190
3.08 IPS
 
Image Segmentation (Q)
98% 271
4.40 IPS
 
Pose Estimation (SP)
100% 687
0.80 IPS
 
Pose Estimation (HP)
100% 710
0.83 IPS
 
Pose Estimation (Q)
84% 471
0.56 IPS
 
Object Detection (SP)
100% 151
12.0 IPS
 
Object Detection (HP)
100% 153
12.1 IPS
 
Object Detection (Q)
83% 188
15.2 IPS
 
Face Detection (SP)
100% 381
4.52 IPS
 
Face Detection (HP)
100% 389
4.62 IPS
 
Face Detection (Q)
95% 505
6.03 IPS
 
Depth Estimation (SP)
100% 442
3.41 IPS
 
Depth Estimation (HP)
99% 511
3.94 IPS
 
Depth Estimation (Q)
64% 472
4.32 IPS
 
Style Transfer (SP)
89% 1386
1.80 IPS
 
Style Transfer (HP)
89% 1393
1.81 IPS
 
Style Transfer (Q)
98% 1294
1.67 IPS
 
Image Super-Resolution (SP)
100% 277
10.2 IPS
 
Image Super-Resolution (HP)
100% 281
10.4 IPS
 
Image Super-Resolution (Q)
97% 278
10.3 IPS
 
Text Classification (SP)
100% 141
187.8 IPS
 
Text Classification (HP)
100% 138
184.8 IPS
 
Text Classification (Q)
88% 149
201.1 IPS
 
Machine Translation (SP)
100% 217
3.74 IPS
 
Machine Translation (HP)
100% 218
3.76 IPS
 
Machine Translation (Q)
50% 92
3.26 IPS
 

Compare

Set Baseline Geekbench 6 now available