Planning on PlanBench Blocksworld Random (test)
92.5Plain Text AccuracyGPT5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT5Prompting=Plain Text, Model Category=LRM2026.02 | 92.5 | — | |
| o1preview*Prompting=Plain Text, Model Category=LRM2026.02 | 37.3 | — | |
| o1Prompting=Plain Text, Model Category=LRM2026.02 | 31.5 | — | |
| o1miniPrompting=Plain Text, Model Category=LRM2026.02 | 9.33 | — | |
| GPT4oPrompting=Plain Text, Model Category=LLM2026.02 | 0.83 | — | |
| GPT4Prompting=Plain Text, Model Category=LLM2026.02 | 0 | — | |
| GPT4Prompting=TMK, Model Category=LLM2026.02 | — | 4.17 | |
| GPT4oPrompting=TMK, Model Category=LLM2026.02 | — | 4.83 | |
| GPT5Prompting=TMK, Model Category=LRM2026.02 | — | 99 | |
| o1Prompting=TMK, Model Category=LRM2026.02 | — | 97.33 | |
| o1miniPrompting=TMK, Model Category=LRM2026.02 | — | 27 |