Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
479
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | February 10 2025 11:21 PM |
| Views | 6 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| 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 | 14.25 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
271
50.7 IPS |
|
|
Image Classification (F16)
|
100% |
272
50.9 IPS |
|
|
Image Classification (I8)
|
97% |
551
103.1 IPS |
|
|
Image Segmentation (F32)
|
100% |
293
4.90 IPS |
|
|
Image Segmentation (F16)
|
100% |
285
4.76 IPS |
|
|
Image Segmentation (I8)
|
98% |
421
7.03 IPS |
|
|
Pose Estimation (F32)
|
100% |
609
0.74 IPS |
|
|
Pose Estimation (F16)
|
100% |
580
0.70 IPS |
|
|
Pose Estimation (I8)
|
100% |
3001
3.63 IPS |
|
|
Object Detection (F32)
|
100% |
289
21.6 IPS |
|
|
Object Detection (F16)
|
100% |
251
18.7 IPS |
|
|
Object Detection (I8)
|
61% |
206
15.4 IPS |
|
|
Face Detection (F32)
|
100% |
401
4.77 IPS |
|
|
Face Detection (F16)
|
100% |
390
4.63 IPS |
|
|
Face Detection (I8)
|
86% |
693
8.24 IPS |
|
|
Depth Estimation (F32)
|
100% |
477
3.70 IPS |
|
|
Depth Estimation (F16)
|
100% |
431
3.35 IPS |
|
|
Depth Estimation (I8)
|
95% |
657
5.10 IPS |
|
|
Style Transfer (F32)
|
100% |
1031
1.36 IPS |
|
|
Style Transfer (F16)
|
100% |
1055
1.39 IPS |
|
|
Style Transfer (I8)
|
98% |
2341
3.08 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
411
14.7 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
345
12.3 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
1766
63.1 IPS |
|
|
Text Classification (F32)
|
100% |
430
618.0 IPS |
|
|
Text Classification (F16)
|
100% |
336
482.2 IPS |
|
|
Text Classification (I8)
|
92% |
464
666.2 IPS |
|
|
Machine Translation (F32)
|
100% |
462
8.49 IPS |
|
|
Machine Translation (F16)
|
100% |
476
8.76 IPS |
|
|
Machine Translation (I8)
|
64% |
84
1.54 IPS |
