Google nirva
Geekbench AI Score
120
Single Precision Score
119
Half Precision Score
64
Quantized Score
Geekbench AI 1.5.0 for Android AArch64
Result Information
| Upload Date | November 05 2025 04:02 AM |
| Views | 3 |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | placeholder |
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google nirva |
| Model ID | Google nirva |
| Motherboard | telithn50 |
| CPU Information | |
|---|---|
| Name | placeholder |
| Topology | 1 Processor, 2 Cores |
| Identifier | ARM implementer 78 architecture 8 variant 2 part 0 revision 1 |
| Base Frequency | 0 MHz |
| Cluster 1 | 2 Cores |
| Memory Information | |
|---|---|
| Size | 6.83 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
79
14.8 IPS |
|
|
Image Classification (HP)
|
100% |
71
13.3 IPS |
|
|
Image Classification (Q)
|
99% |
38
7.18 IPS |
|
|
Image Segmentation (SP)
|
100% |
87
1.41 IPS |
|
|
Image Segmentation (HP)
|
100% |
91
1.48 IPS |
|
|
Image Segmentation (Q)
|
98% |
43
0.69 IPS |
|
|
Pose Estimation (SP)
|
100% |
120
0.14 IPS |
|
|
Pose Estimation (HP)
|
100% |
121
0.14 IPS |
|
|
Pose Estimation (Q)
|
98% |
99
0.12 IPS |
|
|
Object Detection (SP)
|
100% |
70
5.53 IPS |
|
|
Object Detection (HP)
|
100% |
69
5.51 IPS |
|
|
Object Detection (Q)
|
87% |
40
3.22 IPS |
|
|
Face Detection (SP)
|
100% |
202
2.40 IPS |
|
|
Face Detection (HP)
|
100% |
199
2.37 IPS |
|
|
Face Detection (Q)
|
97% |
77
0.92 IPS |
|
|
Depth Estimation (SP)
|
100% |
159
1.22 IPS |
|
|
Depth Estimation (HP)
|
99% |
159
1.22 IPS |
|
|
Depth Estimation (Q)
|
64% |
92
0.84 IPS |
|
|
Style Transfer (SP)
|
100% |
284
0.36 IPS |
|
|
Style Transfer (HP)
|
100% |
285
0.37 IPS |
|
|
Style Transfer (Q)
|
98% |
260
0.34 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
75
2.77 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
74
2.74 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
53
1.97 IPS |
|
|
Text Classification (SP)
|
100% |
99
132.4 IPS |
|
|
Text Classification (HP)
|
100% |
97
129.9 IPS |
|
|
Text Classification (Q)
|
91% |
42
56.6 IPS |
|
|
Machine Translation (SP)
|
100% |
168
2.90 IPS |
|
|
Machine Translation (HP)
|
100% |
170
2.94 IPS |
|
|
Machine Translation (Q)
|
57% |
49
1.19 IPS |
