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

Science Reasoning on GPQA (Score)

81.4Score

DeepSeek v3.2

28.98442.59256.269.808May 26, 2025Jun 29, 2025Aug 2, 2025Sep 6, 2025Oct 10, 2025Nov 13, 2025Dec 18, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
81.4
2025.12
78.8
77.5
2025.12
77.3
2025.12
77
2025.12
74.4
73.3
2025.05
39
2025.05
38
2025.05
35.5
2025.05
35
2025.05
34.5
2025.05
34
2025.05
34
2025.05
33.5
2025.05
33
2025.05
31