M3CoT
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
M3CoT
82.68Accuracy
90
M3CoT
61.2Accuracy
71
M3CoT (test)
91.61Total Acc
55
M3CoT
79.7Accuracy
53
M3CoT
74.2Accuracy
17
M3CoT (test)
78.67Language Science Score
15
M3CoT
82.45NS Score
12
M3CoT social-science and social-commonsense sub-topics
11.99Accuracy Change
12
M3CoT
78.21Pass@1 Accuracy
11
M3CoT Reasoning (subset of 500 samples)
76.4AIM-CoT Win Rate
2