Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Web navigation on WebShop (50 instructions)
Loading...
82.1
Score
Expert
52.668
60.309
67.95
75.591
Oct 6, 2023
Score
SR
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
SR
Expert
type=Human
2023.10
82.1
59.6
LATS (ReAct)
k=30, n=5
2023.10
75.9
38
Fine-tuning
2023.10
67.5
45
Reflexion
k=30
2023.10
64.2
35
IL+RL
type=Reinforcement Lea...
2023.10
62.4
28.7
IL
type=Imitation Learning
2023.10
59.9
29.1
ReAct (best of k)
k=30
2023.10
59.1
32
ReAct
trajectories=1
2023.10
53.8
28
Feedback
Search any
task
Search any
task