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

Multiple Choice Question Answering on SciQ

100Accuracy

QA

2242.2562.582.75Apr 14, 2022Dec 19, 2022Aug 26, 2023May 2, 2024Jan 7, 2025Sep 14, 2025May 22, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2022.09
100-
2022.09
100-
2022.09
98.21-
2022.09
98.09-
2022.09
98.09-
2022.09
98.09-
2022.09
97.96-
2026.02
95.3-
2026.02
95.3-
2022.09
95.28-
2026.02
95.2-
2026.02
95.2-
2026.02
95.1-
2026.02
95.1-
2026.05
95-
2026.02
94.9-
2026.02
94.9-
2026.05
94.9-
2026.02
94.8-
2026.05
94.8-
2026.02
94.6-
2026.02
94.5-
2026.02
94.5-
2026.02
94.2-
2025.07
94-
2025.07
93.9-
2026.02
93.8-
2026.02
93.5-
2025.07
93.1-
2025.07
92.9-
2026.02
92.6-
2025.07
92.5-
2025.07
92.2-
2025.07
90.8-
2025.07
90-
2022.04
89.9-
2025.07
89.4-
2025.07
88.9-
2025.07
88.2-
2022.04
87.5-
2025.11
87.5-
2025.11
87.3-
2022.04
87.1-
2025.11
86.7-
2025.11
86.6-
2025.11
86.1-
2025.11
86-
2022.04
85.9-
2025.11
85.4-
2025.07
84.4-
2025.07
84.3-
2026.02
82.5-
2022.04
81.9-
2026.02
81-
2025.07
80.9-
2026.02
80.6-
2026.02
79.8-
2026.02
78.8-
2026.02
77.7-
2026.02
76.8-
2022.04
75.8-
2022.10
74-
2022.10
73.7-
2022.10
73.2-
2022.10
72.7-
2026.02
69.6-
2026.03
68.4-
2026.02
68.3-
2026.03
67.8-
2026.03
67-
2026.03
66.8-
2026.03
65.8-
2026.03
65.8-
2022.10
64.9-
2026.03
64.8-
2022.10
64-
2022.10
60.8-
2025.07
59.9-
2022.10
58.5-
2022.10
57.7-
2022.10
57.5-
2022.10
51.3-
2022.10
51-
2025.07
49.8-
2022.10
49.5-
2025.07
49.4-
2022.10
48.8-
2022.10
48.6-
2022.10
44.7-
2022.10
42.6-
2022.10
25-