Geekbench AI Score

3220
Single Precision Score
13844
Half Precision Score
14085
Quantized Score
Geekbench AI 1.0.0 for macOS AArch64

Result Information

User FangYuan
Upload Date August 27 2024 03:31 AM
Views 10

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1
System Information
Operating System macOS 15.1 (Build 24B5024e)
Model MacBook Air (Late 2020)
Model IDMacBookAir10,1
Motherboard MacBookAir10,1
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier Apple M1
Base Frequency 3.20 GHz
Cluster 14 Cores
Cluster 24 Cores
Memory Information
Size 8.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1405
261.2 IPS
 
Image Classification (HP)
100% 6292
1.17 KIPS
 
Image Classification (Q)
99% 6562
1.22 KIPS
 
Image Segmentation (SP)
100% 1375
22.3 IPS
 
Image Segmentation (HP)
100% 6182
100.2 IPS
 
Image Segmentation (Q)
100% 6180
100.2 IPS
 
Pose Estimation (SP)
100% 6523
7.61 IPS
 
Pose Estimation (HP)
100% 67998
79.3 IPS
 
Pose Estimation (Q)
94% 64480
75.6 IPS
 
Object Detection (SP)
100% 1511
119.8 IPS
 
Object Detection (HP)
99% 6730
535.3 IPS
 
Object Detection (Q)
91% 6654
531.7 IPS
 
Face Detection (SP)
100% 3022
35.9 IPS
 
Face Detection (HP)
100% 13041
155.0 IPS
 
Face Detection (Q)
100% 14238
169.2 IPS
 
Depth Estimation (SP)
100% 5806
44.7 IPS
 
Depth Estimation (HP)
99% 43798
337.4 IPS
 
Depth Estimation (Q)
97% 46750
361.5 IPS
 
Style Transfer (SP)
100% 16714
21.5 IPS
 
Style Transfer (HP)
100% 118473
152.3 IPS
 
Style Transfer (Q)
100% 123943
159.3 IPS
 
Image Super-Resolution (SP)
100% 3726
137.6 IPS
 
Image Super-Resolution (HP)
100% 23430
865.2 IPS
 
Image Super-Resolution (Q)
98% 24001
889.2 IPS
 
Text Classification (SP)
100% 2306
3.08 KIPS
 
Text Classification (HP)
100% 3979
5.31 KIPS
 
Text Classification (Q)
93% 3895
5.23 KIPS
 
Machine Translation (SP)
100% 2505
43.2 IPS
 
Machine Translation (HP)
100% 2304
39.7 IPS
 
Machine Translation (Q)
98% 2291
39.6 IPS
 

Compare

Set Baseline Geekbench 6 now available