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

Interactive Decision-making on ScienceWorld Unseen (test)

58.94Success Rate

ITPR

-0.28815.088530.46545.8415Jan 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
58.94
2026.01
57.61
2026.01
57.61
2026.01
56.95
2026.01
56.29
2026.01
56.29
2026.01
54.96
2026.01
54.3
2026.01
50.33
2026.01
49.67
2026.01
49
2026.01
47.68
2026.01
27.14
2026.01
19.86
2026.01
19.2
2026.01
17.88
2026.01
17.21
2026.01
16.55
2026.01
13.24
2026.01
9.93
2026.01
8.61
2026.01
4.63
2026.01
3.31
2026.01
1.99