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

Question Answering on OpenBookQA (Accuracy %)

48.47Accuracy

DeepSeek-R1 (BF16)

46.59847.08447.5748.056Dec 5, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
48.47
2025.12
46.67