Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Planning and self-evolution under curriculum setting on PlanCraft
Loading...
72.5
Success Rate (Easy)
ExpeL
60.852
63.876
66.9
69.924
Jun 11, 2026
Success Rate (Easy)
Success Rate (Medium)
Success Rate (Hard)
Overall Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (Easy)
Success Rate (Medium)
Success Rate (Hard)
Overall Success Rate
ExpeL
Backbone LLM=GPT-4.1-m...
2026.06
72.5
50
4.5
43.3
ProPlay
Backbone LLM=GPT-4.1-m...
2026.06
71.2
47.5
10.4
44.4
LATS
Backbone LLM=GPT-4.1-m...
2026.06
70
45
10.4
43.3
Reflexion
Backbone LLM=GPT-4.1-m...
2026.06
66.2
50
9
42.2
Wall-E
Backbone LLM=GPT-4.1-m...
2026.06
63.7
45
7.5
39.6
ReAct
Backbone LLM=GPT-4.1-m...
2026.06
61.3
45
7.5
38.5
WorldCoder
Backbone LLM=GPT-4.1-m...
2026.06
61.3
42.5
7.5
38
Feedback
Search any
task
Search any
task