Geekbench AI Score

2443
Single Precision Score
2445
Half Precision Score
3629
Quantized Score
Geekbench AI 1.2.0 for Windows AVX2

Result Information

Upload Date July 02 2025 06:58 AM
Views 5

System Information

AI Information
Framework OpenVINO
Backend CPU
Device Intel(R) Xeon(R) CPU E3-1270 v5 @ 3.60GHz
System Information
Operating System Windows 10 Pro (64-bit)
Model Supermicro Super Server
Motherboard Supermicro X11SSL-F
CPU Information
Name Intel Xeon E3-1270 v5
Topology 1 Processor, 4 Cores, 8 Threads
Identifier GenuineIntel Family 6 Model 94 Stepping 3
Base Frequency 3.60 GHz
Cluster 14 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1507
280.3 IPS
 
Image Classification (HP)
100% 1512
281.1 IPS
 
Image Classification (Q)
100% 2229
414.6 IPS
 
Image Segmentation (SP)
100% 1495
24.2 IPS
 
Image Segmentation (HP)
100% 1499
24.3 IPS
 
Image Segmentation (Q)
99% 2485
40.4 IPS
 
Pose Estimation (SP)
100% 3009
3.51 IPS
 
Pose Estimation (HP)
100% 3007
3.51 IPS
 
Pose Estimation (Q)
94% 5521
6.48 IPS
 
Object Detection (SP)
100% 1414
112.2 IPS
 
Object Detection (HP)
100% 1429
113.3 IPS
 
Object Detection (Q)
87% 2281
182.9 IPS
 
Face Detection (SP)
100% 2928
34.8 IPS
 
Face Detection (HP)
100% 2937
34.9 IPS
 
Face Detection (Q)
97% 5782
68.9 IPS
 
Depth Estimation (SP)
100% 3878
29.9 IPS
 
Depth Estimation (HP)
99% 3904
30.1 IPS
 
Depth Estimation (Q)
81% 6197
48.9 IPS
 
Style Transfer (SP)
100% 8720
11.2 IPS
 
Style Transfer (HP)
100% 8658
11.1 IPS
 
Style Transfer (Q)
98% 15746
20.3 IPS
 
Image Super-Resolution (SP)
100% 1784
65.9 IPS
 
Image Super-Resolution (HP)
100% 1783
65.8 IPS
 
Image Super-Resolution (Q)
98% 3252
120.5 IPS
 
Text Classification (SP)
100% 1871
2.50 KIPS
 
Text Classification (HP)
100% 1869
2.50 KIPS
 
Text Classification (Q)
91% 1294
1.74 KIPS
 
Machine Translation (SP)
100% 2397
41.3 IPS
 
Machine Translation (HP)
100% 2374
40.9 IPS
 
Machine Translation (Q)
100% 2397
41.3 IPS
 

Compare

Set Baseline Geekbench 6 now available