Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Scientific Question Answering on ScienceQA

88.6Accuracy

MASQuant

-3.54420.37844.368.222May 30, 2024Sep 14, 2024Dec 30, 2024Apr 17, 2025Aug 2, 2025Nov 17, 2025Mar 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
88.6
2026.03
88.5
2026.03
88.4
2026.03
88.2
2026.03
88.1
2026.03
87.8
2026.03
87.8
2026.03
87.8
2026.03
86
2026.03
85.7
2026.03
85.2
2026.03
83.3
2026.03
82.4
2026.03
82.4
2026.03
82.4
2026.03
82.2
2026.03
81.9
2026.03
81.8
2026.03
81.7
2026.03
81.5
2026.03
81.3
2026.03
81.3
2026.03
80.1
2026.03
79.7
2026.03
78.6
2026.03
77.9
2026.03
76.7
2024.05
75.3
2026.03
72.1
2026.03
71.2
2025.06
69.96
2026.03
69.9
2025.06
69.61
2025.06
69.56
2025.06
69.51
2024.05
69.5
2025.06
69.41
2025.06
69.36
2025.06
69.36
2025.06
69.31
2025.06
69.26
2025.06
69.06
2025.06
69.01
2025.06
69.01
2024.05
68.9
2025.06
68.86
2025.06
68.86
2025.06
68.82
2025.06
68.82
2024.05
68.8
2025.06
68.72
2025.06
68.57
2025.06
68.52
2025.06
68.52
2025.06
68.37
2025.06
68.07
2024.05
66.8
2026.03
64.7
2024.05
64.5
2024.05
60.5
2026.03
0