Geekbench AI Score

3212
Single Precision Score
15166
Half Precision Score
15377
Quantized Score
Geekbench AI 1.0.0 for macOS AArch64

Result Information

User BlackSw4an
Upload Date February 03 2025 05:31 PM
Views 6

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1
System Information
Operating System macOS 15.3 (Build 24D60)
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% 1388
258.1 IPS
 
Image Classification (HP)
100% 6412
1.19 KIPS
 
Image Classification (Q)
99% 6677
1.25 KIPS
 
Image Segmentation (SP)
100% 1376
22.3 IPS
 
Image Segmentation (HP)
100% 8379
135.8 IPS
 
Image Segmentation (Q)
100% 8399
136.2 IPS
 
Pose Estimation (SP)
100% 6489
7.57 IPS
 
Pose Estimation (HP)
100% 67440
78.7 IPS
 
Pose Estimation (Q)
94% 65368
76.7 IPS
 
Object Detection (SP)
100% 1507
119.6 IPS
 
Object Detection (HP)
99% 7189
571.9 IPS
 
Object Detection (Q)
91% 6910
552.1 IPS
 
Face Detection (SP)
100% 3010
35.8 IPS
 
Face Detection (HP)
100% 13044
155.0 IPS
 
Face Detection (Q)
100% 13519
160.6 IPS
 
Depth Estimation (SP)
100% 5742
44.2 IPS
 
Depth Estimation (HP)
99% 44297
341.3 IPS
 
Depth Estimation (Q)
97% 47117
364.3 IPS
 
Style Transfer (SP)
100% 16735
21.5 IPS
 
Style Transfer (HP)
100% 118607
152.5 IPS
 
Style Transfer (Q)
100% 124493
160.0 IPS
 
Image Super-Resolution (SP)
100% 3721
137.4 IPS
 
Image Super-Resolution (HP)
100% 23894
882.3 IPS
 
Image Super-Resolution (Q)
98% 24238
898.0 IPS
 
Text Classification (SP)
100% 2330
3.11 KIPS
 
Text Classification (HP)
100% 4145
5.53 KIPS
 
Text Classification (Q)
93% 4030
5.41 KIPS
 
Machine Translation (SP)
100% 2499
43.0 IPS
 
Machine Translation (HP)
100% 3643
62.8 IPS
 
Machine Translation (Q)
98% 3768
65.1 IPS
 

Compare

Set Baseline Geekbench 6 now available