B550M Steel Legend
Geekbench AI Score
24728
Single Precision Score
37271
Half Precision Score
14911
Quantized Score
Geekbench AI 1.5.0 for Windows AVX2
Result Information
| User | crylessengine |
| Upload Date | September 26 2025 10:07 PM |
| Views | 11 |
System Information
| AI Information | |
|---|---|
| Framework | ONNX |
| Backend | DirectML |
| Device | NVIDIA GeForce RTX 3090 |
| System Information | |
|---|---|
| Operating System | Microsoft Windows 11 Pro (64-bit) |
| Model | B550M Steel Legend |
| Motherboard | ASRock B550M Steel Legend |
| Power Plan | AMD Ryzen Balanced |
| CPU Information | |
|---|---|
| Name | AMD Ryzen 9 3950X |
| Topology | 1 Processor, 16 Cores, 32 Threads |
| Identifier | AuthenticAMD Family 23 Model 113 Stepping 0 |
| Base Frequency | 3.50 GHz |
| Cluster 1 | 16 Cores |
| Memory Information | |
|---|---|
| Size | 64.00 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
9256
1.72 KIPS |
|
|
Image Classification (HP)
|
99% |
13252
2.47 KIPS |
|
|
Image Classification (Q)
|
100% |
6308
1.17 KIPS |
|
|
Image Segmentation (SP)
|
100% |
17635
285.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
25734
417.2 IPS |
|
|
Image Segmentation (Q)
|
98% |
12039
195.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
168390
196.5 IPS |
|
|
Pose Estimation (HP)
|
100% |
357373
417.0 IPS |
|
|
Pose Estimation (Q)
|
96% |
127919
149.9 IPS |
|
|
Object Detection (SP)
|
100% |
12364
980.8 IPS |
|
|
Object Detection (HP)
|
100% |
17226
1.37 KIPS |
|
|
Object Detection (Q)
|
85% |
8326
669.8 IPS |
|
|
Face Detection (SP)
|
100% |
33334
396.1 IPS |
|
|
Face Detection (HP)
|
100% |
46744
555.4 IPS |
|
|
Face Detection (Q)
|
97% |
21690
258.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
63847
491.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
107653
829.4 IPS |
|
|
Depth Estimation (Q)
|
77% |
37261
298.4 IPS |
|
|
Style Transfer (SP)
|
100% |
264125
339.5 IPS |
|
|
Style Transfer (HP)
|
100% |
623531
801.6 IPS |
|
|
Style Transfer (Q)
|
98% |
189136
243.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
36984
1.37 KIPS |
|
|
Image Super-Resolution (HP)
|
100% |
51790
1.91 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
21260
787.2 IPS |
|
|
Text Classification (SP)
|
100% |
2621
3.50 KIPS |
|
|
Text Classification (HP)
|
99% |
3306
4.41 KIPS |
|
|
Text Classification (Q)
|
97% |
1349
1.81 KIPS |
|
|
Machine Translation (SP)
|
100% |
4617
79.5 IPS |
|
|
Machine Translation (HP)
|
100% |
4587
79.0 IPS |
|
|
Machine Translation (Q)
|
70% |
1533
28.8 IPS |
