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

Tool-using on NoisyToolBench IMR

1.03Average Steps

AwN

-26.3288158.3431343.015527.6869Aug 31, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.08
1.030.33
2024.08
1.22-
2024.08
1.940.2
2024.08
2.16-
2024.08
2.98-
2024.08
3.08-
2024.08
3.4-
2024.08
3.52-
2024.08
3.60.06
2024.08
3.820.52
2024.08
3.940.2
2024.08
3.960.7
2024.08
3.98-
2024.08
4.02-
2024.08
4.080.36
2024.08
4.10.4
2024.08
4.12-
2024.08
4.36-
2024.08
5.981.1
2024.08
6.360.68
2024.08
7.681.18
2024.08
9.58-
2024.08
9.64-
2024.08
11.240.98
2024.08
12.8-
2024.08
13.080.74
2024.08
17.460.8
2024.08
21.04-
2024.08
24.61.8
2024.08
41.7-
2024.08
532.569.08
2024.08
685-