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

Multiple-choice Question Answering on AQuA

87.4Accuracy

GPT-4o + QuaSAR

67.74472.84777.9583.053Feb 18, 2025Apr 19, 2025Jun 19, 2025Aug 18, 2025Oct 18, 2025Dec 17, 2025Feb 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.02
87.4
2026.02
86.56
2025.02
84.3
2025.02
83.5
2026.02
82.66
2026.02
81.36
2026.02
80.4
2026.02
79.48
2025.02
79.1
2025.02
78.8
2026.02
78.2
2025.02
77.5
2026.02
76.3
2026.02
75.44
2025.02
74
2025.02
73.6
2026.02
73.52
2025.02
72.8
2025.02
72.4
2026.02
72.4
2026.02
71.85
2026.02
71.5
2026.02
71.44
2026.02
71.27
2025.02
70.9
2026.02
70.44
2026.02
70.16
2026.02
69.85
2026.02
69.27
2025.02
69
2026.02
68.5