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

Arithmetic Reasoning on MultiArith

100Accuracy

Previous SoTA

95.8496.929899.08Mar 21, 2022Nov 30, 2022Aug 11, 2023Apr 22, 2024Jan 1, 2025Sep 12, 2025May 25, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2024.10
100--
2022.03
100--
2022.06
99.8--
2023.05
99.7--
2023.05
99.7--
2026.03
99.67--
2023.05
99.3--
2022.06
99.3--
2022.03
99.3--
2023.06
99.3--
2022.11
99.2--
2026.03
99.11--
2023.11
99.1--
2026.02
99.05--
2023.05
99--
2023.05
99--
2024.10
99--
2024.04
99--
2023.06
99--
2026.03
98.93--
2023.05
98.8--
2023.06
98.8--
2026.03
98.8--
2023.05
98.7--
2023.05
98.7--
2023.06
98.7--
2022.06
98.6--
2024.10
98.6--
2023.05
98.5--
2026.05
98.33--
2026.05
98.33--
2026.05
98.33--
2026.05
98.33--
2026.05
98.33--
2026.05
98.33--
2026.05
98.33--
2026.05
98.28--
2023.06
98.23--
2026.05
98.22--
2026.05
98.22--
2023.11
98.1--
2024.04
98.1--
2024.04
98.1--
2023.05
98--
2024.10
98--
2025.11
97.87--
2024.04
97.8--
2024.04
97.8--
2026.02
97.8--
2026.03
97.77--
2026.02
97.6--
2022.10
97.5--
2023.11
97.5--
2026.03
97.5--
2026.03
97.49--
2026.02
97.35--
2026.03
97.33--
2023.06
97.3--
2026.03
97.29--
2026.05
97.22--
2026.05
97.22--
2026.05
97.22--
2026.05
97.22--
2026.05
97.22--
2026.03
97.12--
2024.04
97.1--
2026.03
97.07--
2026.05
97.06--
2026.03
97--
2025.11
96.88--
2026.03
96.85--
2026.03
96.83--
2026.03
96.83--
2026.03
96.79--
2023.06
96.7--
2026.03
96.7--
2026.05
96.61--
2026.03
96.58--
2026.05
96.56--
2026.03
96.5--
2026.03
96.5--
2026.03
96.5--
2025.06
96.5--
2026.03
96.42--
2025.11
96.41--
2022.06
96.4--
2026.03
96.36--
2026.03
96.36--
2026.03
96.31--
2023.05
96.3--
2025.11
96.3--
2025.06
96.3--
2026.02
96.28--
2025.11
96.27--
2026.03
96.22--
2022.03
96.2--
2026.03
96.2--
2026.03
96.03--
2026.03
96.02--
2023.05
96--
Showing 100 of 296 rows