Multi-hop QA on DROP (test)
87.9F1 ScoreDenoiseFlow
Evaluation Results
| Method | Links | |
|---|---|---|
| DenoiseFlowBackbone LLM=GPT-4o-mini, System Category=Autonomous Multi-agent2026.02 | 87.9 | |
| JudgeFlowBackbone LLM=GPT-4o-mini, System Category=Autonomous Multi-agent2026.02 | 86.1 | |
| MermaidFlowBackbone LLM=GPT-4o-mini, System Category=Autonomous Multi-agent2026.02 | 85.5 | |
| MaASBackbone LLM=GPT-4o-mini, System Category=Autonomous Multi-agent2026.02 | 83.1 | |
| DyLANBackbone LLM=GPT-4o-mini, System Category=Hand-crafted Multi-agent2026.02 | 82.2 | |
| GPTSwarmBackbone LLM=GPT-4o-mini, System Category=Autonomous Multi-agent2026.02 | 81 | |
| AFlowBackbone LLM=GPT-4o-mini, System Category=Autonomous Multi-agent2026.02 | 80.6 | |
| LLM-BlenderBackbone LLM=GPT-4o-mini, System Category=Hand-crafted Multi-agent2026.02 | 80.4 | |
| CoT SCBackbone LLM=GPT-4o-mini, System Category=Single-agent2026.02 | 78.8 | |
| CoTBackbone LLM=GPT-4o-mini, System Category=Single-agent2026.02 | 78.5 | |
| LLM-DebateBackbone LLM=GPT-4o-mini, System Category=Hand-crafted Multi-agent2026.02 | 78.1 | |
| ADASBackbone LLM=GPT-4o-mini, System Category=Autonomous Multi-agent2026.02 | 76.6 | |
| Self-RefineBackbone LLM=GPT-4o-mini, System Category=Hand-crafted Multi-agent2026.02 | 70.2 | |
| IOBackbone LLM=GPT-4o-mini, System Category=Single-agent2026.02 | 68.3 |