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

Planning on BlocksWorld (Valid %, Successful %)

100Success Rate

GPT5

-1.9224.545177.46Aug 15, 2025Sep 12, 2025Oct 10, 2025Nov 7, 2025Dec 5, 2025Jan 2, 2026Jan 30, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2025.08
100-
2025.08
98-
92-
80-
2025.08
74-
70-
2026.01
6668
2026.01
6668
2025.08
52-
2026.01
5151
2026.01
4949
2026.01
4850
2026.01
4850
2026.01
4546
2026.01
4050
2026.01
3232
2026.01
3131
2026.01
2525
2026.01
1010
2025.08
2-