Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Navigation on CraftBench (test)
Loading...
41.9
Success Rate (SR)
PPO-UrbanVerse
7.788
16.644
25.5
34.356
Oct 16, 2025
Success Rate (SR)
Completion Time (CT)
Route Completeness (RC)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Completion Time (CT)
Route Completeness (RC)
PPO-UrbanVerse
training_data=160 Urba...
2025.10
41.9
35.5
62.4
MBRA
type=foundation model
2025.10
35.6
25.6
52.9
S2E
type=foundation model
2025.10
33.1
27.7
55.7
CityWalker
type=foundation model
2025.10
29.2
38.2
48.6
Overfitting
training_data=directly...
2025.10
26.5
32.2
40.6
PPO-UrbanSim
training_data=160 Urba...
2025.10
9.1
31.5
19.4
Feedback
Search any
task
Search any
task