Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reactivity Maze on Reactivity Maze (200 episodes)
Loading...
1
Mean Reward
Factive
0.1472
0.3686
0.59
0.8114
Jun 9, 2026
Mean Reward
Success Rate
Safe Rate
Cue Visit Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Reward
Success Rate
Safe Rate
Cue Visit Rate
Factive
2026.06
1
100
0
100
Sophisticated Inference
2026.06
0.96
94
6
100
Standard EFE planning
2026.06
0.56
61
21
66
Fmarginal
2026.06
0.33
0
100
0
Fplanning
2026.06
0.18
17
64
0
Feedback
Search any
task
Search any
task