Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Plancraft

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-agent system task solvingplancraft
Accuracy88.7
21
World ModelingPlancraft
Smelt98.4
20
Planning and self-evolution under curriculum settingPlanCraft
Success Rate (Easy)72.5
7
Sequential PlanningPlanCraft
Performance Change vs. SAS39.1
1
Showing 4 of 4 rows