List your company

Mathematical Reasoning on AMC2023 Kaggle (test)

75Base Accuracyentropy-guided decoding
43.851.96068.1Mar 10, 2026

Evaluation results

MethodLinks
entropy-guided decodingModel=GPT4o2026.037598.251.91275.91.3351
entropy-guided decodingModel=Llama3.1-8B2026.034597.51.62178.61.2116.9