Google Pixel 3a
Geekbench AI Score
115
Single Precision Score
135
Half Precision Score
634
Quantized Score
Geekbench AI 1.0.0 for Android AArch64
Result Information
| User | grinceur |
| Upload Date | August 23 2024 04:09 PM |
| Views | 8 |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | Qualcomm Snapdragon 670 |
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Google Pixel 3a |
| Model ID | Google Pixel 3a |
| Motherboard | sargo |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | Qualcomm Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 6 part 2050 revision 13 |
| Base Frequency | 1.71 GHz |
| Cluster 1 | 6 Cores @ 1.71 GHz |
| Cluster 2 | 2 Cores @ 2.00 GHz |
| Memory Information | |
|---|---|
| Size | 3.51 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
129
23.9 IPS |
|
|
Image Classification (HP)
|
100% |
172
32.0 IPS |
|
|
Image Classification (Q)
|
97% |
472
88.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
169
2.74 IPS |
|
|
Image Segmentation (HP)
|
100% |
55
0.90 IPS |
|
|
Image Segmentation (Q)
|
98% |
672
10.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
310
0.36 IPS |
|
|
Pose Estimation (HP)
|
100% |
714
0.83 IPS |
|
|
Pose Estimation (Q)
|
96% |
4204
4.92 IPS |
|
|
Object Detection (SP)
|
100% |
127
10.1 IPS |
|
|
Object Detection (HP)
|
100% |
45
3.55 IPS |
|
|
Object Detection (Q)
|
89% |
575
46.0 IPS |
|
|
Face Detection (SP)
|
100% |
314
3.74 IPS |
|
|
Face Detection (HP)
|
100% |
121
1.44 IPS |
|
|
Face Detection (Q)
|
97% |
1459
17.4 IPS |
|
|
Depth Estimation (SP)
|
99% |
185
1.42 IPS |
|
|
Depth Estimation (HP)
|
100% |
110
0.85 IPS |
|
|
Depth Estimation (Q)
|
46% |
1118
22.5 IPS |
|
|
Style Transfer (SP)
|
100% |
274
0.35 IPS |
|
|
Style Transfer (HP)
|
100% |
185
0.24 IPS |
|
|
Style Transfer (Q)
|
98% |
1339
1.73 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
190
7.02 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
375
13.9 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
1538
57.0 IPS |
|
|
Text Classification (SP)
|
71% |
2
2.66 IPS |
|
|
Text Classification (HP)
|
100% |
65
86.8 IPS |
|
|
Text Classification (Q)
|
93% |
67
90.3 IPS |
|
|
Machine Translation (SP)
|
100% |
84
1.45 IPS |
|
|
Machine Translation (HP)
|
100% |
115
1.98 IPS |
|
|
Machine Translation (Q)
|
54% |
61
1.72 IPS |
