Geekbench AI Score

3081
Single Precision Score
14865
Half Precision Score
14469
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User min2252
Upload Date March 06 2026 04:15 PM
Views 7

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1
System Information
Operating System macOS 26.3 (Build 25D125)
Model MacBook Pro (13-inch Late 2020)
Model IDMacBookPro17,1
Motherboard MacBookPro17,1
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% 1285
239.0 IPS
 
Image Classification (HP)
100% 6294
1.17 KIPS
 
Image Classification (Q)
96% 5961
1.11 KIPS
 
Image Segmentation (SP)
100% 1306
21.2 IPS
 
Image Segmentation (HP)
100% 8884
144.0 IPS
 
Image Segmentation (Q)
99% 9180
148.8 IPS
 
Pose Estimation (SP)
100% 6021
7.03 IPS
 
Pose Estimation (HP)
100% 67324
78.6 IPS
 
Pose Estimation (Q)
95% 64410
75.5 IPS
 
Object Detection (SP)
100% 1387
110.0 IPS
 
Object Detection (HP)
99% 6839
544.0 IPS
 
Object Detection (Q)
91% 6327
505.5 IPS
 
Face Detection (SP)
100% 2973
35.3 IPS
 
Face Detection (HP)
100% 13643
162.1 IPS
 
Face Detection (Q)
100% 12385
147.2 IPS
 
Depth Estimation (SP)
100% 5474
42.2 IPS
 
Depth Estimation (HP)
99% 44894
345.9 IPS
 
Depth Estimation (Q)
85% 45529
355.8 IPS
 
Style Transfer (SP)
100% 16525
21.2 IPS
 
Style Transfer (HP)
100% 121344
156.0 IPS
 
Style Transfer (Q)
96% 114159
147.3 IPS
 
Image Super-Resolution (SP)
100% 3454
127.5 IPS
 
Image Super-Resolution (HP)
100% 24226
894.5 IPS
 
Image Super-Resolution (Q)
99% 24197
893.5 IPS
 
Text Classification (SP)
100% 2399
3.20 KIPS
 
Text Classification (HP)
99% 4256
5.68 KIPS
 
Text Classification (Q)
93% 4248
5.70 KIPS
 
Machine Translation (SP)
100% 2473
42.6 IPS
 
Machine Translation (HP)
100% 2672
46.0 IPS
 
Machine Translation (Q)
98% 2726
47.1 IPS
 

Compare

Set Baseline Geekbench 6 now available