Geekbench AI Score

1657
Single Precision Score
3356
Half Precision Score
6426
Quantized Score
Geekbench AI 1.7.0 for Windows AArch64

Result Information

User tbanks
Upload Date October 27 2026 06:19 AM
Views 9

System Information

AI Information
Framework ONNX
Backend CPU
Device NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU)
System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model ASUS ProArt P16 H7607BA
Motherboard ASUSTeK COMPUTER INC. H7607BA
Power PlanBalanced
CPU Information
Name NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU)
Topology 1 Processor, 20 Cores
Identifier ARMv8 (64-bit) Family 8 Model D87 Revision 1
Base Frequency 4.00 GHz
Cluster 110 Cores
Cluster 210 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 543
100.9 IPS
 
Image Classification (HP)
100% 2406
447.4 IPS
 
Image Classification (Q)
99% 3460
645.3 IPS
 
Image Segmentation (SP)
100% 844
13.7 IPS
 
Image Segmentation (HP)
100% 3404
55.2 IPS
 
Image Segmentation (Q)
98% 7323
119.1 IPS
 
Pose Estimation (SP)
100% 4746
5.54 IPS
 
Pose Estimation (HP)
100% 10255
12.0 IPS
 
Pose Estimation (Q)
94% 29374
34.4 IPS
 
Object Detection (SP)
100% 741
58.8 IPS
 
Object Detection (HP)
99% 2671
212.5 IPS
 
Object Detection (Q)
86% 4114
330.7 IPS
 
Face Detection (SP)
100% 1826
21.7 IPS
 
Face Detection (HP)
100% 5984
71.1 IPS
 
Face Detection (Q)
97% 9326
111.2 IPS
 
Depth Estimation (SP)
100% 2202
17.0 IPS
 
Depth Estimation (HP)
98% 4629
35.8 IPS
 
Depth Estimation (Q)
79% 11527
91.6 IPS
 
Style Transfer (SP)
100% 11057
14.2 IPS
 
Style Transfer (HP)
100% 14217
18.3 IPS
 
Style Transfer (Q)
98% 40943
52.8 IPS
 
Image Super-Resolution (SP)
100% 1985
73.3 IPS
 
Image Super-Resolution (HP)
100% 1596
58.9 IPS
 
Image Super-Resolution (Q)
99% 4535
167.9 IPS
 
Text Classification (SP)
100% 876
1.17 KIPS
 
Text Classification (HP)
100% 516
689.0 IPS
 
Text Classification (Q)
97% 808
1.08 KIPS
 
Machine Translation (SP)
100% 1259
21.7 IPS
 
Machine Translation (HP)
99% 2498
43.2 IPS
 
Machine Translation (Q)
65% 2435
48.9 IPS
 

Compare

Set Baseline Geekbench AI now available