Geekbench AI Score

218
Single Precision Score
312
Half Precision Score
235
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Hulkstern
Upload Date March 11 2025 10:30 AM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device placeholder
System Information
Operating System Android 13
Model Google nissa
Model IDGoogle nissa
Motherboard yavijo
CPU Information
Name placeholder
Topology 1 Processor, 4 Cores
Identifier ARM implementer 78 architecture 8 variant 2 part 0 revision 1
Base Frequency 0 MHz
Cluster 14 Cores
Memory Information
Size 3.08 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 151
28.1 IPS
 
Image Classification (HP)
100% 211
39.3 IPS
 
Image Classification (Q)
96% 205
38.3 IPS
 
Image Segmentation (SP)
100% 189
3.06 IPS
 
Image Segmentation (HP)
100% 305
4.95 IPS
 
Image Segmentation (Q)
98% 259
4.22 IPS
 
Pose Estimation (SP)
100% 236
0.28 IPS
 
Pose Estimation (HP)
100% 428
0.50 IPS
 
Pose Estimation (Q)
94% 409
0.48 IPS
 
Object Detection (SP)
100% 123
9.73 IPS
 
Object Detection (HP)
100% 164
13.0 IPS
 
Object Detection (Q)
86% 161
12.9 IPS
 
Face Detection (SP)
100% 406
4.82 IPS
 
Face Detection (HP)
100% 617
7.34 IPS
 
Face Detection (Q)
96% 563
6.72 IPS
 
Depth Estimation (SP)
100% 322
2.48 IPS
 
Depth Estimation (HP)
99% 513
3.95 IPS
 
Depth Estimation (Q)
63% 417
3.89 IPS
 
Style Transfer (SP)
100% 766
0.99 IPS
 
Style Transfer (HP)
100% 1296
1.67 IPS
 
Style Transfer (Q)
98% 1271
1.64 IPS
 
Image Super-Resolution (SP)
100% 156
5.76 IPS
 
Image Super-Resolution (HP)
100% 272
10.0 IPS
 
Image Super-Resolution (Q)
97% 247
9.14 IPS
 
Text Classification (SP)
100% 100
133.2 IPS
 
Text Classification (HP)
100% 100
133.3 IPS
 
Text Classification (Q)
91% 42
56.2 IPS
 
Machine Translation (SP)
100% 191
3.29 IPS
 
Machine Translation (HP)
100% 178
3.06 IPS
 
Machine Translation (Q)
57% 49
1.19 IPS
 

Compare

Set Baseline Geekbench 6 now available