Geekbench AI Score

36377
Single Precision Score
53770
Half Precision Score
28069
Quantized Score
Geekbench AI 1.3.0 for Windows AVX2

Result Information

Upload Date August 24 2025 02:17 AM
Views 5

System Information

AI Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce RTX 4080
System Information
Operating System Microsoft Windows 11 Pro for Workstations (64-bit)
Model Gigabyte Technology Co., Ltd. TRX50 AI TOP
Motherboard Gigabyte Technology Co., Ltd. TRX50 AI TOP
Power PlanBalanced
CPU Information
Name AMD Ryzen Threadripper 7960X 24-Cores
Topology 1 Processor, 24 Cores, 48 Threads
Identifier AuthenticAMD Family 25 Model 24 Stepping 1
Base Frequency 4.20 GHz
Cluster 124 Cores
Memory Information
Size 128.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 13596
2.53 KIPS
 
Image Classification (HP)
99% 19225
3.59 KIPS
 
Image Classification (Q)
100% 11873
2.21 KIPS
 
Image Segmentation (SP)
100% 26191
424.6 IPS
 
Image Segmentation (HP)
100% 35645
577.8 IPS
 
Image Segmentation (Q)
98% 24223
393.9 IPS
 
Pose Estimation (SP)
100% 265249
309.5 IPS
 
Pose Estimation (HP)
100% 523215
610.5 IPS
 
Pose Estimation (Q)
96% 232442
272.3 IPS
 
Object Detection (SP)
100% 17206
1.36 KIPS
 
Object Detection (HP)
100% 24448
1.94 KIPS
 
Object Detection (Q)
85% 15027
1.21 KIPS
 
Face Detection (SP)
100% 52137
619.5 IPS
 
Face Detection (HP)
100% 69881
830.3 IPS
 
Face Detection (Q)
97% 44827
534.5 IPS
 
Depth Estimation (SP)
100% 84944
654.4 IPS
 
Depth Estimation (HP)
99% 157499
1.22 KIPS
 
Depth Estimation (Q)
78% 64973
518.9 IPS
 
Style Transfer (SP)
100% 401670
516.4 IPS
 
Style Transfer (HP)
100% 913842
1.17 KIPS
 
Style Transfer (Q)
98% 352426
454.4 IPS
 
Image Super-Resolution (SP)
100% 56714
2.09 KIPS
 
Image Super-Resolution (HP)
100% 77486
2.86 KIPS
 
Image Super-Resolution (Q)
99% 43395
1.61 KIPS
 
Text Classification (SP)
100% 3690
4.93 KIPS
 
Text Classification (HP)
99% 4503
6.01 KIPS
 
Text Classification (Q)
97% 2260
3.03 KIPS
 
Machine Translation (SP)
100% 6707
115.5 IPS
 
Machine Translation (HP)
100% 6568
113.1 IPS
 
Machine Translation (Q)
70% 3002
56.3 IPS
 

Compare

Set Baseline Geekbench 6 now available