Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Emergency evacuation dialogue on Wildfire Evacuation Overall (Full (train + New))
Loading...
92
Success Rate
IQL (Ours)
49.36
60.43
71.5
82.57
Jul 2, 2026
Success Rate
Avg Dialogue Turns
Updated 22d ago
Evaluation Results
Method
Method
Links
Success Rate
Avg Dialogue Turns
IQL (Ours)
2026.07
92
11.2
Zero-shot
mode=zero-shot
2026.07
88
11.9
IQL-Global
variant=global
2026.07
86
13
IQL-Persona
variant=persona
2026.07
80
12.9
RAG
2026.07
78
11.8
Random-10
policy_index=10
2026.07
78
11.8
Random-6
policy_index=6
2026.07
72
12.3
Random-9
policy_index=9
2026.07
71
12.9
Random-8
policy_index=8
2026.07
69
12.5
Cross-Policy
2026.07
51
13.6
Feedback
Search any
task
Search any
task