List your company

Planning on PlanBench Mystery Blocksworld

87.3Success RateLlama 3.1-8B with symbolic feedback
-3.49220.07943.6567.221Jun 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 Downward2026.0687.3
GLM-5Planning Mode=Direct generation (LLM-only)2026.0682
Claude 4.6Planning Mode=Direct generation (LLM-only)2026.0660.5
DeepSeek-R1Planning Mode=Direct generation (LLM-only)2026.0643.3
GPT-5.2Planning Mode=Direct generation (LLM-only)2026.066.2
GPT-4oPlanning Mode=Direct generation (LLM-only)2026.060
Claude 3.5Planning Mode=Direct generation (LLM-only)2026.060