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

Scientific Reasoning on Materials

78Average Score @16 (1h)

GRPO

35.04846.19957.3568.501Jan 28, 2026Feb 7, 2026Feb 18, 2026Mar 1, 2026Mar 11, 2026Mar 22, 2026Apr 2, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.04
7878.9-80.1
2026.04
75.779.1-81.3
2026.04
74.979.2-81.5
2026.04
74.777.6-77.8
2026.01
74.377.1--
2026.04
74.374.3-74.3
2026.01
73.974.1--
2026.01
73.779.1--
2026.01
73.373.5--
2026.01
72.178.4--
2026.01
70.975--
2026.04
68.176.6-76.6
2026.04
61.2---
2026.04
59.3---
2026.01
58.9---
2026.01
36.7---
2026.01
--58.9-
2026.01
--74.3-
2026.01
--77.1-
2026.01
--73.3-
2026.01
--75.8-
2026.01
--72.1-
2026.01
--78.3-
2026.01
--36.7-
2026.01
--73.8-
2026.01
--78.1-
2026.01
--67.9-
2026.01
--74.4-
2026.01
--75.3-
2026.01
--79.2-