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

Mathematical Reasoning on GSM8K (test) (Speedup, τ)

2.23Speedup

DEER

1.90761.99132.0752.1587Dec 17, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
2.232.7
2025.12
1.922.43