Planning on PlanBench Blocksworld (Classic) (test)
99.3Plain Text AccGPT5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT5Prompting=Plain Text, Model Category=LRM, Shots=Best of Zero & One shot2026.02 | 99.3 | — | |
| o1preview*Prompting=Plain Text, Model Category=LRM, Shots=Best of Zero & One shot2026.02 | 97.8 | — | |
| o1Prompting=Plain Text, Model Category=LRM, Shots=Best of Zero & One shot2026.02 | 95.7 | — | |
| o1miniPrompting=Plain Text, Model Category=LRM, Shots=Best of Zero & One shot2026.02 | 56.7 | — | |
| GPT4oPrompting=Plain Text, Model Category=LLM, Shots=Best of Zero & One shot2026.02 | 35.5 | — | |
| GPT4Prompting=Plain Text, Model Category=LLM, Shots=Best of Zero & One shot2026.02 | 34.6 | — | |
| GPT4Prompting=TMK, Model Category=LLM, Shots=One shot2026.02 | — | 39.7 | |
| GPT4oPrompting=TMK, Model Category=LLM, Shots=One shot2026.02 | — | 45.3 | |
| GPT5Prompting=TMK, Model Category=LRM, Shots=One shot2026.02 | — | 99.7 | |
| o1Prompting=TMK, Model Category=LRM, Shots=One shot2026.02 | — | 98.5 | |
| o1miniPrompting=TMK, Model Category=LRM, Shots=One shot2026.02 | — | 57 |