Geekbench AI Score

609
Single Precision Score
1010
Half Precision Score
781
Quantized Score
Geekbench AI 1.8.0 for Android AArch64

Result Information

Upload Date November 22 2026 11:38 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 16
Model INFINIX Infinix X6876
Model IDINFINIX Infinix X6876
Motherboard Infinix-X6876
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 24 Cores @ 2.60 GHz
Memory Information
Size 7.27 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 251
46.6 IPS
 
Image Classification (HP)
100% 562
104.5 IPS
 
Image Classification (Q)
97% 518
96.6 IPS
 
Image Segmentation (SP)
100% 665
10.8 IPS
 
Image Segmentation (HP)
100% 1187
19.2 IPS
 
Image Segmentation (Q)
98% 1021
16.6 IPS
 
Pose Estimation (SP)
100% 2553
2.98 IPS
 
Pose Estimation (HP)
100% 4639
5.41 IPS
 
Pose Estimation (Q)
95% 4502
5.28 IPS
 
Object Detection (SP)
100% 297
23.6 IPS
 
Object Detection (HP)
99% 497
39.4 IPS
 
Object Detection (Q)
83% 486
39.2 IPS
 
Face Detection (SP)
100% 1288
15.3 IPS
 
Face Detection (HP)
100% 2002
23.8 IPS
 
Face Detection (Q)
96% 1691
20.2 IPS
 
Depth Estimation (SP)
100% 1712
13.2 IPS
 
Depth Estimation (HP)
98% 2856
22.1 IPS
 
Depth Estimation (Q)
62% 2256
21.4 IPS
 
Style Transfer (SP)
100% 4459
5.73 IPS
 
Style Transfer (HP)
100% 7860
10.1 IPS
 
Style Transfer (Q)
98% 7928
10.2 IPS
 
Image Super-Resolution (SP)
100% 849
31.4 IPS
 
Image Super-Resolution (HP)
100% 1259
46.5 IPS
 
Image Super-Resolution (Q)
97% 1405
52.1 IPS
 
Text Classification (SP)
35% 16
144.4 IPS
 
Text Classification (HP)
35% 22
197.3 IPS
 
Text Classification (Q)
29% 12
212.8 IPS
 
Machine Translation (SP)
100% 417
7.19 IPS
 
Machine Translation (HP)
100% 580
10.00 IPS
 
Machine Translation (Q)
43% 144
8.35 IPS
 

Compare

Set Baseline Geekbench AI now available