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

Question Answering on OpenBookQA

94.4Accuracy

LMSI

71.31277.30683.389.294May 2, 2020Apr 20, 2021Apr 9, 2022Mar 29, 2023Mar 17, 2024Mar 6, 2025Feb 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2022.10
94.4--
2022.10
93--
2022.10
92--
2022.10
91--
2026.01
90.8--
2026.01
90.8--
2026.01
90.4--
2022.10
90--
2026.01
90--
2024.09
89.8--
2024.09
88.8--
2024.09
88.4--
2024.03
87.71--
2024.03
87.61--
2020.05
87.2--
2024.04
86.9--
2022.10
86.4--
2020.05
86--
2026.01
85.8--
2026.01
85.6--
2024.09
85.4--
2024.04
85--
2024.04
84.8--
2024.04
84.5--
2022.10
84.4--
2024.09
84.4--
2026.01
84.4--
2020.05
84.2--
2020.05
84.2--
2026.01
84.2--
2024.09
83.5--
2024.04
83.4--
2024.04
83.2--
2024.04
83--
2024.03
82.66--
2024.04
81.6--
2026.01
81.6--
2026.01
81.4--
2024.03
80.92--
2024.04
80.9--
2024.04
80.6--
2024.04
80.6--
2024.04
80.4--
2020.05
80--
2025.01
80--
2025.01
80--
2022.12
79.9--
2026.02
79.3--
2025.01
79--
2025.01
79--
2025.01
79--
2025.01
79--
2025.01
79--
2025.01
79--
2024.09
78.6--
2026.01
78.4--
2025.01
78--
2025.01
78--
2025.01
78--
2025.01
78--
2026.01
78--
2024.09
77.5--
2022.12
77.4--
2022.12
77.2--
2025.01
77--
2025.01
77--
2025.01
77--
2025.01
77--
2025.01
77--
2025.01
77--
2025.01
77--
2022.12
76.7--
2022.12
76.5--
2023.11
76.4--
2026.02
76.2--
2025.01
76--
2025.01
76--
2025.01
76--
2025.01
76--
2025.01
76--
2025.01
76--
2025.01
76--
2025.01
76--
2025.01
76--
2025.01
76--
2025.05
76--
2024.04
75.8--
2020.05
75.7--
2024.04
75.4--
2025.01
75--
2025.01
75--
2025.01
74--
2025.01
74--
2025.01
74--
2026.02
73.5--
2025.01
73--
2025.05
72.8--
2022.10
72.54--
2026.02
72.2--
2026.01
72.2--
Showing 100 of 469 rows