Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Autonomous Agent Task Solving on AgentBoard Science World
Loading...
58.9
Task Completion Rate
ReAct
29.988
37.494
45
52.506
Jun 5, 2026
Task Completion Rate
Average Progress
Updated 1mo ago
Evaluation Results
Method
Method
Links
Task Completion Rate
Average Progress
ReAct
LLM backbone=Claude Ha...
2026.06
58.9
82.58
AdMem
LLM backbone=Claude Ha...
2026.06
56.7
84.47
AWM
LLM backbone=Claude Ha...
2026.06
31.1
63.24
Feedback
Search any
task
Search any
task