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

Mathematical Reasoning on GSM8K (Robustness/Adversarial Evaluation)

72.5Clean Accuracy

AGLS

30.941.752.563.3May 26, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
72.517.575.869.45
2025.05
505901.49
2025.05
47.51568.423.44
2025.05
32.52.592.311.84