Geekbench AI Score

36734
Single Precision Score
54293
Half Precision Score
28208
Quantized Score
Geekbench AI 1.4.0 for Windows AVX2

Result Information

Upload Date August 12 2025 03:25 PM
Views 6

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% 13567
2.52 KIPS
 
Image Classification (HP)
99% 19078
3.56 KIPS
 
Image Classification (Q)
100% 11845
2.20 KIPS
 
Image Segmentation (SP)
100% 26296
426.3 IPS
 
Image Segmentation (HP)
100% 35715
579.0 IPS
 
Image Segmentation (Q)
98% 24198
393.5 IPS
 
Pose Estimation (SP)
100% 268620
313.4 IPS
 
Pose Estimation (HP)
100% 534775
624.0 IPS
 
Pose Estimation (Q)
96% 238058
278.9 IPS
 
Object Detection (SP)
100% 17764
1.41 KIPS
 
Object Detection (HP)
100% 25442
2.02 KIPS
 
Object Detection (Q)
85% 15293
1.23 KIPS
 
Face Detection (SP)
100% 52833
627.8 IPS
 
Face Detection (HP)
100% 70938
842.9 IPS
 
Face Detection (Q)
97% 44741
533.5 IPS
 
Depth Estimation (SP)
100% 86060
663.0 IPS
 
Depth Estimation (HP)
99% 159566
1.23 KIPS
 
Depth Estimation (Q)
78% 65216
520.8 IPS
 
Style Transfer (SP)
100% 402400
517.3 IPS
 
Style Transfer (HP)
100% 913906
1.17 KIPS
 
Style Transfer (Q)
98% 352190
454.1 IPS
 
Image Super-Resolution (SP)
100% 57224
2.11 KIPS
 
Image Super-Resolution (HP)
100% 79024
2.92 KIPS
 
Image Super-Resolution (Q)
99% 43499
1.61 KIPS
 
Text Classification (SP)
100% 3766
5.03 KIPS
 
Text Classification (HP)
99% 4487
5.99 KIPS
 
Text Classification (Q)
97% 2262
3.03 KIPS
 
Machine Translation (SP)
100% 6666
114.8 IPS
 
Machine Translation (HP)
100% 6546
112.7 IPS
 
Machine Translation (Q)
70% 3023
56.7 IPS
 

Compare

Set Baseline Geekbench 6 now available