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

Interactive Decision Making on ScienceWorld Seen (val)

0.7349Average Reward

AdaPlan-H

0.2745960.3940980.51360.633102Apr 25, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
0.7349
2026.04
0.6608
2026.04
0.6527
2026.04
0.6454
2026.04
0.5884
2026.04
0.5876
2026.04
0.5798
2026.04
0.5764
2026.04
0.5724
2026.04
0.5423
2026.04
0.4817
2026.04
0.4573
2026.04
0.4367
2026.04
0.4303
2026.04
0.4246
2026.04
0.4127
2026.04
0.3618
2026.04
0.3308
2026.04
0.3103
2026.04
0.2923