Delivery Task on Delivery Task 5000-step simulation
69.48Profit (Avg)DeepSeek-V3
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek-V32025.11 | 69.48 | 16.77 | 2.1 | 0.47 | 0.34 | 0.07 | 2.33 | 0.47 | 8 | 3 | |
| Claude-3.5-Sonnet2025.11 | 69.07 | 20.69 | 2.73 | 1.1 | 0.54 | 0.2 | 11.33 | 8.39 | 9 | 3.46 | |
| GPT-4o2025.11 | 43.91 | 14.16 | 1.63 | 0.43 | 0.3 | 0.06 | 0.67 | 0.47 | 4.67 | 0.47 | |
| Gemini-2.5-Flash2025.11 | 42.42 | 3.1 | 2.1 | 0.17 | 0.17 | 0.04 | 2.67 | 1.25 | 2 | 2 | |
| Gemini-2.0-Flash2025.11 | 28.72 | 12.04 | 1.53 | 0.58 | 0.11 | 0.03 | 0.67 | 0.47 | 0.67 | 1 | |
| Qwen3-32B2025.11 | 24.73 | 7.95 | 1.37 | 0.13 | 0.4 | 0.17 | 1.33 | 0.47 | 5.33 | 2.06 | |
| DeepSeek-Prover-V22025.11 | 21.66 | 7.18 | 0.67 | 0.14 | 0.42 | 0.03 | 7.33 | 8.39 | 1 | 1 | |
| QwQ2025.11 | 17.31 | 4.07 | 0.87 | 0.2 | 0.41 | 0.2 | 0.33 | 0.47 | 3.33 | 2.52 | |
| GPT-4o-mini2025.11 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |