Personalized Planning on MAP-PPL (test)
2.12AtpsAutoAgents
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AutoAgentsCategory=Generic MAS framework planners2026.06 | 2.12 | 3 | 63 | 71 | 28 | 34 | 3 | 33 | 75 | 35 | 92 | |
| AFlowCategory=Agentic workflow planners2026.06 | 2.06 | 1 | 56 | 79 | 26 | 40 | 6 | 33 | 36 | 42 | 89 | |
| AIPOMCategory=Agentic workflow planners2026.06 | 2.03 | 1 | 58 | 79 | 31 | 33 | 2 | 35 | 55 | 40 | 81 | |
| Claude Opus 4.6Category=Frontier LLM planners2026.06 | 1.09 | 4 | 64 | 59 | 67 | 39 | 24 | 55 | 26 | 39 | 81 | |
| Qwen3-MaxCategory=Frontier LLM planners2026.06 | 1.06 | 0 | 61 | 75 | 49 | 29 | 22 | 47 | 46 | 20 | 81 | |
| AutoGenCategory=Generic MAS framework planners2026.06 | 1.04 | 1 | 61 | 76 | 29 | 37 | 8 | 31 | 84 | 38 | 83 | |
| PersonalPlanBackbone=Qwen3-8B-Instruct2026.06 | 1.03 | 0 | 69 | 82 | 70 | 48 | 24 | 61 | 88 | 36 | 77 | |
| GPT-5.4Category=Frontier LLM planners2026.06 | 1 | 0 | 55 | 43 | 53 | 47 | 10 | 62 | 35 | 33 | 90 | |
| PersonalPlanBackbone=Qwen3-32B-Instruct2026.06 | 1 | 0 | 74 | 81 | 76 | 57 | 22 | 65 | 82 | 56 | 92 |