Geekbench AI Score

3259
Single Precision Score
16753
Half Precision Score
16564
Quantized Score
Geekbench AI 1.5.0 for macOS AArch64

Result Information

User iambjlu
Upload Date November 06 2025 04:15 PM
Views 1

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1
System Information
Operating System macOS 15.2 (Build 24C5057p)
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 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1396
259.7 IPS
 
Image Classification (HP)
100% 6360
1.18 KIPS
 
Image Classification (Q)
96% 5993
1.12 KIPS
 
Image Segmentation (SP)
100% 1396
22.6 IPS
 
Image Segmentation (HP)
100% 9872
160.0 IPS
 
Image Segmentation (Q)
99% 10185
165.1 IPS
 
Pose Estimation (SP)
100% 6530
7.62 IPS
 
Pose Estimation (HP)
100% 68916
80.4 IPS
 
Pose Estimation (Q)
95% 66057
77.4 IPS
 
Object Detection (SP)
100% 1523
120.8 IPS
 
Object Detection (HP)
99% 7554
600.9 IPS
 
Object Detection (Q)
91% 7052
563.5 IPS
 
Face Detection (SP)
100% 3034
36.1 IPS
 
Face Detection (HP)
100% 16049
190.7 IPS
 
Face Detection (Q)
100% 15790
187.6 IPS
 
Depth Estimation (SP)
100% 5812
44.8 IPS
 
Depth Estimation (HP)
99% 49416
380.7 IPS
 
Depth Estimation (Q)
85% 49636
387.9 IPS
 
Style Transfer (SP)
100% 17124
22.0 IPS
 
Style Transfer (HP)
100% 122352
157.3 IPS
 
Style Transfer (Q)
96% 116267
150.0 IPS
 
Image Super-Resolution (SP)
100% 3810
140.7 IPS
 
Image Super-Resolution (HP)
100% 23986
885.7 IPS
 
Image Super-Resolution (Q)
99% 24705
912.3 IPS
 
Text Classification (SP)
100% 2332
3.11 KIPS
 
Text Classification (HP)
100% 4042
5.40 KIPS
 
Text Classification (Q)
93% 4022
5.40 KIPS
 
Machine Translation (SP)
100% 2600
44.8 IPS
 
Machine Translation (HP)
100% 5664
97.6 IPS
 
Machine Translation (Q)
98% 6042
104.4 IPS
 

Compare

Set Baseline Geekbench 6 now available