Geekbench AI Score

3730
Single Precision Score
16421
Half Precision Score
16099
Quantized Score
Geekbench AI 1.3.0 for macOS AArch64

Result Information

Upload Date April 13 2025 06:18 AM
Views 2

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1 Pro
System Information
Operating System macOS 15.3.2 (Build 24D81)
Model MacBook Pro (14-inch, 2021)
Model IDMacBookPro18,3
Motherboard MacBookPro18,3
CPU Information
Name Apple M1 Pro
Topology 1 Processor, 8 Cores
Identifier Apple M1 Pro
Base Frequency 3.22 GHz
Cluster 16 Cores
Cluster 22 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1321
245.6 IPS
 
Image Classification (HP)
100% 7004
1.30 KIPS
 
Image Classification (Q)
96% 6571
1.23 KIPS
 
Image Segmentation (SP)
100% 1592
25.8 IPS
 
Image Segmentation (HP)
100% 9687
157.0 IPS
 
Image Segmentation (Q)
99% 10348
167.7 IPS
 
Pose Estimation (SP)
100% 11155
13.0 IPS
 
Pose Estimation (HP)
100% 70457
82.2 IPS
 
Pose Estimation (Q)
95% 65894
77.2 IPS
 
Object Detection (SP)
100% 1586
125.8 IPS
 
Object Detection (HP)
99% 8041
639.6 IPS
 
Object Detection (Q)
91% 7457
595.8 IPS
 
Face Detection (SP)
100% 3209
38.1 IPS
 
Face Detection (HP)
100% 15829
188.1 IPS
 
Face Detection (Q)
100% 13139
156.1 IPS
 
Depth Estimation (SP)
100% 5926
45.7 IPS
 
Depth Estimation (HP)
99% 50831
391.6 IPS
 
Depth Estimation (Q)
85% 53167
415.5 IPS
 
Style Transfer (SP)
100% 22341
28.7 IPS
 
Style Transfer (HP)
100% 120053
154.3 IPS
 
Style Transfer (Q)
96% 116317
150.1 IPS
 
Image Super-Resolution (SP)
100% 4345
160.4 IPS
 
Image Super-Resolution (HP)
100% 26023
960.9 IPS
 
Image Super-Resolution (Q)
99% 28149
1.04 KIPS
 
Text Classification (SP)
100% 2285
3.05 KIPS
 
Text Classification (HP)
100% 3974
5.30 KIPS
 
Text Classification (Q)
93% 3954
5.31 KIPS
 
Machine Translation (SP)
100% 3328
57.3 IPS
 
Machine Translation (HP)
100% 3713
64.0 IPS
 
Machine Translation (Q)
98% 3871
66.9 IPS
 

Compare

Set Baseline Geekbench 6 now available