List your company

Constrained navigation on FlightQA

32.2AccuracySiRA
-1.2887.40616.124.794Jul 31, 2025

Evaluation results

MethodLinks
SiRAReasoning System=System II, Policy=Simulative Reasoning2025.0732.236.732.238.91.14018.91.1
SiRAReasoning System=System I, Policy=Reactive Policy2025.0714.415.614.416.7037.844.41.1
Unconstrained CoTPlanner=o3-mini2025.073.34.43.34.43.351.132.28.9
Unconstrained CoTPlanner=o12025.071.11.11.11.111.14037.810
OpenHands BrowsingAgentMethod=OpenHands BrowsingAgent2025.0700003.33.3093.3