Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cross-benchmark aggregate ranking on ScienceWorld, τ-Bench, and PlanCraft
Loading...
1.6
Aggregate Rank
ProPlay
1.448
2.474
3.5
4.526
Jun 11, 2026
Aggregate Rank
Updated 1mo ago
Evaluation Results
Method
Method
Links
Aggregate Rank
ProPlay
Backbone LLM=GPT-4.1-m...
2026.06
1.6
Reflexion
Backbone LLM=GPT-4.1-m...
2026.06
3.1
ExpeL
Backbone LLM=GPT-4.1-m...
2026.06
3.3
Wall-E
Backbone LLM=GPT-4.1-m...
2026.06
4.4
LATS
Backbone LLM=GPT-4.1-m...
2026.06
4.8
ReAct
Backbone LLM=GPT-4.1-m...
2026.06
5.3
WorldCoder
Backbone LLM=GPT-4.1-m...
2026.06
5.4
Feedback
Search any
task
Search any
task
