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

Tool-using on NoisyToolBench IMKI

1.26Average Steps

DFSDT

-28.7216173.6542376.03578.4058Aug 31, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.08
1.26-
2024.08
1.3-
2024.08
1.88-
2024.08
2.04-
2024.08
2.50.16
2024.08
2.540.22
2024.08
2.64-
2024.08
3-
2024.08
3.34-
2024.08
3.540.42
2024.08
3.620.44
2024.08
3.740.18
2024.08
3.860.62
2024.08
3.880.2
2024.08
3.940.16
2024.08
4-
2024.08
4-
2024.08
4.2-
2024.08
4.46-
2024.08
5.360.66
2024.08
5.98-
2024.08
6.440.42
2024.08
6.70.86
2024.08
6.740.76
2024.08
9.820.48
2024.08
12.82-
2024.08
15.861.16
2024.08
16.941.44
2024.08
59.08-
2024.08
83.96-
2024.08
445.165.34
2024.08
750.8-