Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Autonomous Driving Reasoning on Dolphins
Loading...
48.95
GS Score
GUARDAD
44.79
45.87
46.95
48.03
May 11, 2026
GS Score
QS Score
Updated 22d ago
Evaluation Results
Method
Method
Links
GS Score
QS Score
GUARDAD
Safeguard Method=GA
2026.05
48.95
30.34
AD-MLLM + SA
Safeguard Method=SA
2026.05
47.67
29.4
AD-MLLM + CM
Safeguard Method=CM
2026.05
45.75
28.62
AD-MLLM + RF
Safeguard Method=RF
2026.05
45.67
28.56
Vanilla AD-MLLM
Safeguard Method=Vanilla
2026.05
44.95
28.43
Feedback
Search any
task
Search any
task