Samsung Galaxy S21 Ultra 5G
Geekbench AI Score
569
Single Precision Score
952
Half Precision Score
770
Quantized Score
Geekbench AI 1.5.0 for Android AArch64
Result Information
| Upload Date | November 12 2025 08:53 PM |
| Views | 3 |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Samsung Exynos 2100 |
| System Information | |
|---|---|
| Operating System | Android 15 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998B |
| Motherboard | exynos2100 |
| Governor | energy_step |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
| Base Frequency | 2.21 GHz |
| Cluster 1 | 4 Cores @ 2.21 GHz |
| Cluster 2 | 3 Cores @ 2.81 GHz |
| Cluster 3 | 1 Core @ 2.91 GHz |
| Memory Information | |
|---|---|
| Size | 10.33 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
343
63.8 IPS |
|
|
Image Classification (HP)
|
100% |
647
120.3 IPS |
|
|
Image Classification (Q)
|
97% |
598
111.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
669
10.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
1287
20.9 IPS |
|
|
Image Segmentation (Q)
|
98% |
1062
17.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
3230
3.77 IPS |
|
|
Pose Estimation (HP)
|
100% |
5359
6.25 IPS |
|
|
Pose Estimation (Q)
|
95% |
5206
6.10 IPS |
|
|
Object Detection (SP)
|
100% |
264
20.9 IPS |
|
|
Object Detection (HP)
|
99% |
450
35.7 IPS |
|
|
Object Detection (Q)
|
83% |
476
38.5 IPS |
|
|
Face Detection (SP)
|
100% |
1367
16.2 IPS |
|
|
Face Detection (HP)
|
100% |
2112
25.1 IPS |
|
|
Face Detection (Q)
|
96% |
1798
21.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
1310
10.1 IPS |
|
|
Depth Estimation (HP)
|
98% |
2220
17.2 IPS |
|
|
Depth Estimation (Q)
|
62% |
1746
16.6 IPS |
|
|
Style Transfer (SP)
|
100% |
4793
6.16 IPS |
|
|
Style Transfer (HP)
|
100% |
9219
11.9 IPS |
|
|
Style Transfer (Q)
|
98% |
8993
11.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
775
28.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1527
56.4 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
1451
53.8 IPS |
|
|
Text Classification (SP)
|
29% |
10
171.5 IPS |
|
|
Text Classification (HP)
|
29% |
14
244.3 IPS |
|
|
Text Classification (Q)
|
29% |
14
239.9 IPS |
|
|
Machine Translation (SP)
|
100% |
275
4.73 IPS |
|
|
Machine Translation (HP)
|
100% |
333
5.74 IPS |
|
|
Machine Translation (Q)
|
43% |
82
4.77 IPS |
