Geekbench AI Score

4122
Single Precision Score
27185
Half Precision Score
30381
Quantized Score
Geekbench AI 1.5.0 for macOS AArch64

Result Information

Upload Date November 25 2025 04:13 PM
Views 5

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Max
System Information
Operating System macOS 15.7.1 (Build 24G231)
Model MacBook Pro (16-inch, 2023)
Model IDMac14,6
Motherboard Mac14,6
CPU Information
Name Apple M2 Max
Topology 1 Processor, 12 Cores
Identifier Apple M2 Max
Base Frequency 3.68 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 96.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1392
258.9 IPS
 
Image Classification (HP)
100% 13997
2.60 KIPS
 
Image Classification (Q)
96% 16732
3.12 KIPS
 
Image Segmentation (SP)
100% 1641
26.6 IPS
 
Image Segmentation (HP)
100% 19622
318.1 IPS
 
Image Segmentation (Q)
99% 24867
403.1 IPS
 
Pose Estimation (SP)
100% 13029
15.2 IPS
 
Pose Estimation (HP)
100% 105837
123.5 IPS
 
Pose Estimation (Q)
95% 104891
122.9 IPS
 
Object Detection (SP)
100% 1682
133.4 IPS
 
Object Detection (HP)
99% 16206
1.29 KIPS
 
Object Detection (Q)
91% 17660
1.41 KIPS
 
Face Detection (SP)
100% 3484
41.4 IPS
 
Face Detection (HP)
100% 35553
422.4 IPS
 
Face Detection (Q)
100% 46017
546.8 IPS
 
Depth Estimation (SP)
100% 6113
47.1 IPS
 
Depth Estimation (HP)
99% 87611
675.0 IPS
 
Depth Estimation (Q)
85% 110451
863.1 IPS
 
Style Transfer (SP)
100% 25198
32.4 IPS
 
Style Transfer (HP)
100% 204380
262.7 IPS
 
Style Transfer (Q)
96% 190365
245.7 IPS
 
Image Super-Resolution (SP)
100% 5041
186.2 IPS
 
Image Super-Resolution (HP)
100% 42475
1.57 KIPS
 
Image Super-Resolution (Q)
99% 50724
1.87 KIPS
 
Text Classification (SP)
100% 2365
3.16 KIPS
 
Text Classification (HP)
100% 4148
5.54 KIPS
 
Text Classification (Q)
93% 4091
5.49 KIPS
 
Machine Translation (SP)
100% 4427
76.3 IPS
 
Machine Translation (HP)
100% 4173
71.9 IPS
 
Machine Translation (Q)
98% 4330
74.8 IPS
 

Compare

Set Baseline Geekbench 6 now available