Geekbench AI Score

3207
Single Precision Score
13743
Half Precision Score
13995
Quantized Score
Geekbench AI 1.0.0 for macOS AArch64

Result Information

User FangYuan
Upload Date August 25 2024 04:43 PM
Views 17

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% 1402
260.7 IPS
 
Image Classification (HP)
100% 6257
1.16 KIPS
 
Image Classification (Q)
99% 6501
1.21 KIPS
 
Image Segmentation (SP)
100% 1361
22.1 IPS
 
Image Segmentation (HP)
100% 6165
99.9 IPS
 
Image Segmentation (Q)
100% 6172
100.1 IPS
 
Pose Estimation (SP)
100% 6537
7.63 IPS
 
Pose Estimation (HP)
100% 67506
78.8 IPS
 
Pose Estimation (Q)
94% 64462
75.6 IPS
 
Object Detection (SP)
100% 1510
119.7 IPS
 
Object Detection (HP)
99% 6751
537.1 IPS
 
Object Detection (Q)
91% 6677
533.5 IPS
 
Face Detection (SP)
100% 3039
36.1 IPS
 
Face Detection (HP)
100% 13028
154.8 IPS
 
Face Detection (Q)
100% 14063
167.1 IPS
 
Depth Estimation (SP)
100% 5813
44.8 IPS
 
Depth Estimation (HP)
99% 43629
336.1 IPS
 
Depth Estimation (Q)
97% 46989
363.3 IPS
 
Style Transfer (SP)
100% 16640
21.4 IPS
 
Style Transfer (HP)
100% 118655
152.5 IPS
 
Style Transfer (Q)
100% 123997
159.4 IPS
 
Image Super-Resolution (SP)
100% 3702
136.7 IPS
 
Image Super-Resolution (HP)
100% 23100
853.0 IPS
 
Image Super-Resolution (Q)
98% 23455
869.0 IPS
 
Text Classification (SP)
100% 2272
3.03 KIPS
 
Text Classification (HP)
100% 3853
5.14 KIPS
 
Text Classification (Q)
93% 3842
5.16 KIPS
 
Machine Translation (SP)
100% 2472
42.6 IPS
 
Machine Translation (HP)
100% 2278
39.2 IPS
 
Machine Translation (Q)
98% 2261
39.1 IPS
 

Compare

Set Baseline Geekbench AI now available