Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multistep Reasoning on MUSR object (test)
Loading...
68.9
Accuracy
Induced
38.428
46.339
54.25
62.161
Jun 2, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Induced
2026.06
68.9
Program-of-Thoughts
2026.06
60.4
Hand
2026.06
58.5
AWM
2026.06
53.8
ReAct
2026.06
50
CoT
2026.06
39.6
Feedback
Search any
task
Search any
task
