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

Interactive Agent Task on ScienceWorld

11.5Efficiency Factor

AGORA

0.8923.6466.49.154May 26, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.05
11.50.016
2026.05
3.60.0002
2026.05
3.40.0077
2026.05
3.30.0009
2026.05
3.20.0082
2026.05
3.20.0002
2026.05
30.0082
2026.05
30.001
2026.05
2.90.0003
2026.05
2.90.001
2026.05
1.80.0006
2026.05
1.50.0146
2026.05
1.40.0019
2026.05
1.30.0006
2026.05
1.30.0023