PlanBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Planning | PlanBench | Accuracy99.1 | 47 | |
| Planning | PlanBench Mystery Blocksworld | Success Rate87.3 | 7 | |
| Planning | PlanBench Mystery | Planning Coverage65.5 | 6 | |
| Planning | PlanBench Blocksworld | Planning Coverage100 | 6 | |
| Planning | PlanBench (in-distribution) | Success Rate97.8 | 6 | |
| Planning | PlanBench Blocksworld Random (test) | Plain Text Accuracy92.5 | 6 | |
| Planning | PlanBench Blocksworld (Classic) (test) | Plain Text Acc99.3 | 6 | |
| Plan Completion | PlanBench Task 8 - Blocks World | Plan Completion Score14.7 | 4 |
Showing 8 of 8 rows