Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Autonomous Driving Evaluation on Composite (New York City)
Loading...
97.3
Completion Rate (CR)
w/o fine-tuning
69.948
77.049
84.15
91.251
Jun 27, 2026
Completion Rate (CR)
Recall Rate (RR)
Success Score (SS)
Operational Rate (OR)
Recovery Factor (RF)
Composite Score (Comp)
Target Success (TS)
Accuracy (ACC)
Yield Value (YV)
LI Score
Overall Score (OS)
Updated 26d ago
Evaluation Results
Method
Method
Links
Completion Rate (CR)
Recall Rate (RR)
Success Score (SS)
Operational Rate (OR)
Recovery Factor (RF)
Composite Score (Comp)
Target Success (TS)
Accuracy (ACC)
Yield Value (YV)
LI Score
Overall Score (OS)
w/o fine-tuning
Fine-tuning=None
2026.06
97.3
59.1
16.8
10.8
11.4
29.6
72.8
73.4
85.8
69.6
29.9
ChatScene
Fine-tuning scenarios=...
2026.06
73.4
38.4
0
0
36.1
44.2
64.3
59.2
80.1
50.9
31.4
TRAFFICALIGN
Fine-tuning scenarios=...
2026.06
71
37.8
0
0
80
59.5
25.8
56.8
50.1
39.9
36.6
Feedback
Search any
task
Search any
task