Planning on NATURALPLAN
80.71Partial AccuracySERO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SEROBackbone=Gemini-2.5-flash-lite2026.05 | 80.71 | 56.78 | |
| Static DAG MASBackbone=Gemini-2.5-flash-lite2026.05 | 77.68 | 54.7 | |
| WorkflowBackbone=Gemini-2.5-flash-lite2026.05 | 72.57 | 51.15 | |
| Static Role OrchestrationBackbone=Gemini-2.5-flash-lite2026.05 | 70.04 | 43.93 | |
| Random Role EvolutionBackbone=Gemini-2.5-flash-lite2026.05 | 63.41 | 40.7 | |
| CoTBackbone=Gemini-2.5-flash-lite2026.05 | 59.34 | 30.96 | |
| SC@3Backbone=Gemini-2.5-flash-lite2026.05 | 59.29 | 30.48 | |
| SEROBackbone=GPT-4o-mini2026.05 | 57.82 | 30.37 | |
| WorkflowBackbone=GPT-4o-mini2026.05 | 57.16 | 24.78 | |
| Static Role OrchestrationBackbone=GPT-4o-mini2026.05 | 56.91 | 28.15 | |
| Static DAG MASBackbone=GPT-4o-mini2026.05 | 55.99 | 21.11 | |
| Random Role EvolutionBackbone=GPT-4o-mini2026.05 | 55.11 | 25.26 | |
| Static DAG MASBackbone=Qwen3-8b2026.05 | 54.9 | 20.3 | |
| SC@3Backbone=GPT-4o-mini2026.05 | 50.61 | 22.15 | |
| WorkflowBackbone=Qwen3-8b2026.05 | 50.42 | 15.78 | |
| CoTBackbone=GPT-4o-mini2026.05 | 50.26 | 22.11 | |
| Static Role OrchestrationBackbone=Qwen3-8b2026.05 | 47.92 | 13.59 | |
| SEROBackbone=Qwen3-8b2026.05 | 46.44 | 14.96 | |
| SC@3Backbone=Qwen3-8b2026.05 | 46.19 | 13.81 | |
| CoTBackbone=Qwen3-8b2026.05 | 46.1 | 13.81 | |
| Random Role EvolutionBackbone=Qwen3-8b2026.05 | 39.28 | 10.26 |