Debt Collection Negotiation on DCN
100DCGPT-4o
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-4o2025.02 | 100 | 4.65 | 100 | 95.76 | 27 | 128.4 | 297.2 | 6.18 | 85.18 | 90 | 84.4 | 58 | 77.4 | |
| o1-miniReasoning model=true2025.02 | 100 | 4.68 | 94 | 94.61 | 29.52 | 140.52 | 352.52 | 5.58 | 83.8 | 89 | 80.7 | 61.9 | 76 | |
| Claude-3.52025.02 | 100 | 4.59 | 98 | 93.3 | 34.92 | 140.52 | 312.32 | 3.32 | 87.3 | 89 | 81.6 | 69.8 | 78.9 | |
| MiniMax2025.02 | 100 | 4.75 | 96 | 92.77 | 38.66 | 167.66 | 401.26 | 7.12 | 76.44 | 88 | 77.6 | 59.1 | 73 | |
| SenseChat2025.02 | 100 | 4.7 | 98 | 89.28 | 34.56 | 155.76 | 354.56 | 5.24 | 81.14 | 87 | 79.1 | 66.1 | 76.1 | |
| Deepseek-V32025.02 | 100 | 4.85 | 99 | 91.65 | 28.4 | 141.2 | 313.6 | 5.42 | 83.82 | 89 | 81.8 | 62.5 | 77.1 | |
| Human2025.02 | 100 | 4.93 | 100 | 98.5 | 16.73 | 119.49 | 260.9 | 3.81 | 78.49 | 86 | 87 | 73.6 | 84 | |
| GPT-4o-mini2025.02 | 99 | 4.61 | 96 | 96.32 | 31.6 | 131.2 | 312 | 6.3 | 84.08 | 89 | 83.6 | 58.9 | 77.1 | |
| Doubao-pro2025.02 | 98 | 4.91 | 96 | 93.11 | 21.22 | 143.02 | 365.22 | 5.98 | 83.68 | 89 | 81.4 | 60.3 | 76 | |
| Deepseek-R1Reasoning model=true2025.02 | 98 | 4.81 | 98 | 93.1 | 37.72 | 146.32 | 348.12 | 5.68 | 83.94 | 88 | 80.2 | 62.4 | 75.9 | |
| Qwen-2.5-72BModel scale=72B2025.02 | 96 | 4.75 | 98 | 88.5 | 36.98 | 185.18 | 404.98 | 3.76 | 78.84 | 83 | 76.4 | 76.7 | 76.4 | |
| Qwen-2.5-7BModel scale=7B2025.02 | 94 | 4.57 | 98 | 87.15 | 46.04 | 214.04 | 436.84 | 2.82 | 79.46 | 84 | 73.2 | 79.3 | 74.3 | |
| Qwen-2.5-14BModel scale=14B2025.02 | 94 | 4.6 | 96 | 89.62 | 28.6 | 154.6 | 358.8 | 3.38 | 79.82 | 88 | 79.3 | 61.3 | 74.9 | |
| LLaMa-3-8BModel scale=8B2025.02 | 91 | 3.64 | 100 | 89.01 | 51.36 | 184.02 | 399.02 | 3.38 | 88.02 | 87 | 75.6 | 71.3 | 74.7 | |
| LLaMa-3-70BModel scale=70B2025.02 | 87 | 3.94 | 98 | 92.24 | 36.72 | 157.32 | 371.12 | 4.5 | 79.56 | 87 | 79.2 | 69.5 | 77.1 |