Samsung SM-S926B (Galaxy S21 Ultra 16/512 variant). samsung SM-S926B
Geekbench AI Score
377
Single Precision Score
480
Half Precision Score
534
Quantized Score
Geekbench AI 1.4.0 for Android AArch64
Result Information
| User | EurasianDynasty |
| Upload Date | July 10 2025 06:02 PM |
| Views | 13 |
| Notes | Running OneAI custom ROM. |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | ARM ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 15 |
| Model | samsung SM-S926B |
| Model ID | samsung SM-S926B |
| Motherboard | exynos2100 |
| Governor | schedutil |
| 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 @ 2.99 GHz |
| Memory Information | |
|---|---|
| Size | 14.27 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
159
29.6 IPS |
|
|
Image Classification (HP)
|
100% |
149
27.7 IPS |
|
|
Image Classification (Q)
|
99% |
379
70.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
389
6.30 IPS |
|
|
Image Segmentation (HP)
|
100% |
471
7.64 IPS |
|
|
Image Segmentation (Q)
|
98% |
347
5.65 IPS |
|
|
Pose Estimation (SP)
|
100% |
1648
1.92 IPS |
|
|
Pose Estimation (HP)
|
100% |
5960
6.95 IPS |
|
|
Pose Estimation (Q)
|
98% |
1345
1.57 IPS |
|
|
Object Detection (SP)
|
100% |
170
13.5 IPS |
|
|
Object Detection (HP)
|
100% |
170
13.5 IPS |
|
|
Object Detection (Q)
|
87% |
552
44.2 IPS |
|
|
Face Detection (SP)
|
100% |
421
5.00 IPS |
|
|
Face Detection (HP)
|
100% |
431
5.12 IPS |
|
|
Face Detection (Q)
|
97% |
982
11.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
360
2.77 IPS |
|
|
Depth Estimation (HP)
|
99% |
364
2.80 IPS |
|
|
Depth Estimation (Q)
|
64% |
982
8.91 IPS |
|
|
Style Transfer (SP)
|
100% |
780
1.00 IPS |
|
|
Style Transfer (HP)
|
100% |
594
0.76 IPS |
|
|
Style Transfer (Q)
|
98% |
827
1.07 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
656
24.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
925
34.2 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
771
28.6 IPS |
|
|
Text Classification (SP)
|
100% |
101
135.0 IPS |
|
|
Text Classification (HP)
|
100% |
262
349.1 IPS |
|
|
Text Classification (Q)
|
91% |
90
121.0 IPS |
|
|
Machine Translation (SP)
|
100% |
430
7.40 IPS |
|
|
Machine Translation (HP)
|
100% |
408
7.02 IPS |
|
|
Machine Translation (Q)
|
57% |
352
8.59 IPS |
