List your company

Planning on NL-PDDL-Bench Logistics

78Planner Success RateLlama 3.1-8B with symbolic feedback
20.17635.18850.265.212Jun 29, 2026

Evaluation results

MethodLinks
Llama 3.1-8B with symbolic feedbackPlanning Mode=Planner-backed formalization, Backbone=LoRA Llama 3.1-8B, External Planner=Fast Downward2026.0678
DeepSeek-R1Planning Mode=Direct generation (LLM-only)2026.0656.8
Claude 4.6Planning Mode=Direct generation (LLM-only)2026.0656.1
GPT-5.2Planning Mode=Direct generation (LLM-only)2026.0642.3
GLM-5Planning Mode=Direct generation (LLM-only)2026.0623.2
Claude 3.5Planning Mode=Direct generation (LLM-only)2026.0622.6
GPT-4oPlanning Mode=Direct generation (LLM-only)2026.0622.4