DriveGPT4-V2: Harnessing Large Language Model Capabilities for Enhanced Closed-Loop Autonomous Driving
Open paper
Benchmark
Model
Rank
Results
carla-longest6-on-carla
DriveGPT4-V2
–
Driving Score: 70
Route Completion: 91
Infraction Score: 0.77
Rank counts only results with a code link.