Planning on PlanBench Mystery
65.5Planning CoverageDeepSeek-R1
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-R1Mode=LLM-fb2026.06 | 65.5 | |
| DeepSeek-R1Mode=LLM-direct2026.06 | 43.3 | |
| Claude-3-5Mode=LLM-fb2026.06 | 4 | |
| GPT-4oMode=LLM-fb2026.06 | 3.8 | |
| GPT-4oMode=LLM-direct2026.06 | 0 | |
| Claude-3-5Mode=LLM-direct2026.06 | 0 |