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

Text-based Scientific Reasoning on ScienceWorld (Seen)

0.8498Average Reward

DELTAMEM

0.7684720.7895860.81070.831814Jun 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
0.8498
2026.06
0.8452
2026.06
0.8052
2026.06
0.7942
2026.06
0.7716