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

Scientific Evaluation on SciEval

87.5Accuracy

o4-mini

82.50883.80485.186.396Aug 26, 2025
Updated 5d ago

Evaluation Results

MethodLinks
2025.08
87.50.4
2025.08
87.4-
2025.08
87.1-
2025.08
86.4-
2025.08
86.1-1.3
2025.08
85.8-
2025.08
85.80
2025.08
85.1-1.3
2025.08
84.8-
2025.08
83.8-
2025.08
83.4-0.4
2025.08
82.7-2.1