Long-form Dialogue on SCM4LLMs
91.08QualityDYCP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DYCPAgent=GPT-4.12026.01 | 91.08 | 0.77 | |
| Full ContextAgent=GPT-4.12026.01 | 90.83 | 1.91 | |
| DYCPAgent=Claude 3.72026.01 | 88.92 | 2.52 | |
| DYCPAgent=Claude 4.02026.01 | 88.19 | 1.79 | |
| Full ContextAgent=Claude 3.72026.01 | 88.08 | 6.3 | |
| DYCPAgent=GPT-4o2026.01 | 87.57 | 1.03 | |
| SeComAgent=Claude 3.72026.01 | 86.32 | 3.54 | |
| Full ContextAgent=GPT-4o2026.01 | 85.51 | 2.06 | |
| SeComAgent=GPT-4o2026.01 | 85.4 | 0.79 | |
| Full ContextAgent=Claude 4.02026.01 | 84.89 | 3.25 | |
| DYCPAgent=GPT-4o mini2026.01 | 84.55 | 0.99 | |
| SCM4LLMsAgent=GPT-4o mini2026.01 | 84.38 | 4.22 | |
| MemoChatAgent=GPT-4o2026.01 | 83.47 | 3.52 | |
| SeComAgent=GPT-4o mini2026.01 | 83.09 | 0.74 | |
| Full ContextAgent=GPT-4o mini2026.01 | 83.08 | 1.63 | |
| DYCPAgent=Mistral-Nemo-Instruct (128k)2026.01 | 80.68 | 1.15 | |
| SCM4LLMsAgent=Claude 3.72026.01 | 79.56 | 7.82 | |
| MemoChatAgent=Claude 3.72026.01 | 78.49 | 7.48 | |
| MemoChatAgent=GPT-4o mini2026.01 | 78.42 | 3.24 | |
| SCM4LLMsAgent=GPT-4o2026.01 | 76.11 | 3.43 | |
| DYCPAgent=Qwen2.5-7B-Instruct (1M)2026.01 | 75.62 | 0.77 | |
| Full ContextAgent=Qwen2.5-7B-Instruct (1M)2026.01 | 74.92 | 4.41 | |
| Full ContextAgent=Mistral-Nemo-Instruct (128k)2026.01 | 71.06 | 7.3 | |
| CondMemAgent=Mistral-Nemo-Instruct (128k)2026.01 | 65.1 | 5.57 | |
| No ContextAgent=GPT-4.12026.01 | 62.41 | 0.43 | |
| CondMemAgent=Qwen2.5-7B-Instruct (1M)2026.01 | 60.08 | 10.36 | |
| No ContextAgent=GPT-4o mini2026.01 | 59.62 | 0.53 | |
| No ContextAgent=Qwen2.5-7B-Instruct (1M)2026.01 | 58.57 | 0.05 | |
| No ContextAgent=GPT-4o2026.01 | 58.47 | 0.45 | |
| No ContextAgent=Claude 3.72026.01 | 57.9 | 1.57 | |
| No ContextAgent=Claude 4.02026.01 | 57.89 | 1.57 | |
| No ContextAgent=Mistral-Nemo-Instruct (128k)2026.01 | 55.28 | 0.07 |