Geekbench AI Score

15310
Single Precision Score
19528
Half Precision Score
17414
Quantized Score
Geekbench AI 1.1.0 for macOS AArch64

Result Information

Upload Date November 21 2024 08:09 AM
Views 3

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M3 Max
System Information
Operating System macOS 15.1.1 (Build 24B91)
Model MacBook Pro (16-inch, Nov 2023)
Model IDMac15,11
Motherboard Mac15,11
CPU Information
Name Apple M3 Max
Topology 1 Processor, 14 Cores
Identifier Apple M3 Max
Base Frequency 4.04 GHz
Cluster 110 Cores
Cluster 24 Cores
Memory Information
Size 36.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 7229
1.34 KIPS
 
Image Classification (HP)
100% 7846
1.46 KIPS
 
Image Classification (Q)
97% 6729
1.26 KIPS
 
Image Segmentation (SP)
100% 13753
222.9 IPS
 
Image Segmentation (HP)
100% 14630
237.2 IPS
 
Image Segmentation (Q)
99% 15120
245.1 IPS
 
Pose Estimation (SP)
100% 66972
78.1 IPS
 
Pose Estimation (HP)
100% 69416
81.0 IPS
 
Pose Estimation (Q)
95% 65827
77.2 IPS
 
Object Detection (SP)
100% 7310
579.9 IPS
 
Object Detection (HP)
100% 7843
622.1 IPS
 
Object Detection (Q)
91% 6595
527.0 IPS
 
Face Detection (SP)
100% 26763
318.0 IPS
 
Face Detection (HP)
100% 31101
369.5 IPS
 
Face Detection (Q)
100% 22798
270.9 IPS
 
Depth Estimation (SP)
100% 32812
252.8 IPS
 
Depth Estimation (HP)
99% 34874
268.7 IPS
 
Depth Estimation (Q)
85% 28392
221.9 IPS
 
Style Transfer (SP)
100% 144113
185.3 IPS
 
Style Transfer (HP)
100% 160815
206.7 IPS
 
Style Transfer (Q)
96% 150117
193.7 IPS
 
Image Super-Resolution (SP)
100% 21578
796.8 IPS
 
Image Super-Resolution (HP)
100% 22528
831.9 IPS
 
Image Super-Resolution (Q)
99% 18507
683.4 IPS
 
Text Classification (SP)
100% 2767
3.69 KIPS
 
Text Classification (HP)
100% 4665
6.23 KIPS
 
Text Classification (Q)
93% 4678
6.28 KIPS
 
Machine Translation (SP)
100% 1924
33.1 IPS
 
Machine Translation (HP)
98% 7042
121.7 IPS
 
Machine Translation (Q)
98% 6903
119.3 IPS
 

Compare

Set Baseline Geekbench 6 now available