Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Rationale Generation on ScienceQA (test)
Loading...
97
B-1
MMCOT
3.92
28.085
52.25
76.415
Oct 25, 2023
B-1
B-4
R-L
Similarity
Relevance
Correctness
Completeness
Coherence
Explainability
Updated 1mo ago
Evaluation Results
Method
Method
Links
B-1
B-4
R-L
Similarity
Relevance
Correctness
Completeness
Coherence
Explainability
MMCOT
w/o GT-R=false
2023.10
97
93
97
99
70.83
67.99
64.81
57.94
58.73
DDCoT
w/o GT-R=true
2023.10
14.7
4.1
28.7
60.1
92
86.38
85.71
84.33
83.26
GPT-3
w/o GT-R=true
2023.10
7.5
1.8
24.9
54.8
81.01
75.99
65.54
61.64
60.32
Feedback
Search any
task
Search any
task
