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

Semantic Parsing on COGS (test)

99Exact Match Accuracy

Full FT

45.9659.7373.587.27Jun 5, 2023Dec 8, 2023Jun 12, 2024Dec 16, 2024Jun 21, 2025Dec 25, 2025Jun 30, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.06
99
2026.06
98.92
2026.06
98.84
2026.06
98.68
2026.06
98.64
2026.06
98.48
2023.06
92.3
2026.06
92.12
2023.06
91.8
87.6
2023.06
85.9
84.6
2024.02
83.36
2024.02
82.6
82.05
2024.02
82
2023.06
82
2023.06
81.4
2023.06
81.1
78.4
2023.06
64.1
2023.06
55.4
2023.06
48