Flowchart-Oriented Dialogue on FLODIAL 1.0 (Root-init)
100INGALlama-3.3-70B
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama-3.3-70BMethod Category=Graph Serialization2026.02 | 100 | |
| Deepseek-R1Method Category=FloCA2026.02 | 100 | |
| Claude Opus 4.1Method Category=RAG-enhanced Graph Serialization2026.02 | 98.85 | |
| GPT-4oMethod Category=RAG-enhanced Graph Serialization2026.02 | 98.85 | |
| GPT-4oMethod Category=FloCA2026.02 | 98.85 | |
| Claude Opus 4.1Method Category=Graph Serialization2026.02 | 98.57 | |
| GPT-4oMethod Category=Graph Serialization2026.02 | 98.28 | |
| GPT-5Method Category=FloCA2026.02 | 98.28 | |
| Llama-3.3-70BMethod Category=FloCA2026.02 | 97.42 | |
| Claude Opus 4.1Method Category=FloCA2026.02 | 97.42 | |
| Qwen3Method Category=FloCA2026.02 | 97.42 | |
| GPT-5Method Category=Graph Serialization2026.02 | 94.85 | |
| GPT-5Method Category=RAG-enhanced Graph Serialization2026.02 | 94.85 | |
| SA-FloNet2026.02 | 93.71 | |
| Deepseek-R1Method Category=RAG-enhanced Graph Serialization2026.02 | 93.71 | |
| Deepseek-R1Method Category=Graph Serialization2026.02 | 89.71 | |
| Qwen3Method Category=RAG-enhanced Graph Serialization2026.02 | 88.57 | |
| Llama-3.3-70BMethod Category=RAG-enhanced Graph Serialization2026.02 | 86 | |
| Claude Opus 4.1Method Category=Visual Language Models2026.02 | 85.71 | |
| GPT-5Method Category=Visual Language Models2026.02 | 82.57 | |
| Qwen3Method Category=Graph Serialization2026.02 | 78 | |
| Qwen-VL-MaxMethod Category=Visual Language Models2026.02 | 71.14 | |
| GPT-4oMethod Category=Visual Language Models2026.02 | 59.71 |