Option Strategy Performance Evaluation on Option Strategy Evaluation Set
60.9Win RateDeepSeek-V3
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DeepSeek-V3Size=Large, Strategy Selection=Top2026.03 | 60.9 | 31.6 | 19.5 | 359.776 | 41.8 | |
| DeepSeek-V3Size=Large, Strategy Selection=All2026.03 | 58 | 31.4 | 18 | 368.143 | 35.8 | |
| Gemini-2.5-FlashSize=Large, Strategy Selection=All2026.03 | 55.8 | 36.1 | 19.1 | 418.192 | 27 | |
| Gemini-2.5-FlashSize=Large, Strategy Selection=Top2026.03 | 55.2 | 37.4 | 22.4 | 331.914 | 72.9 | |
| Qwen3-8BSize=Small, Strategy Selection=Top2026.03 | 54.6 | 42.1 | 27 | 174.551 | 40.3 | |
| DeepSeek-Coder-6.7BSize=Small, Strategy Selection=Top2026.03 | 50.4 | 40.5 | 27.5 | 301.386 | 25.7 | |
| DeepSeek-Coder-6.7BSize=Small, Strategy Selection=All2026.03 | 50.3 | 40.1 | 23.9 | 305.907 | 21.7 | |
| GPT-4.1-MiniSize=Large, Strategy Selection=Top2026.03 | 48.9 | 45.2 | 30.6 | 172.547 | 55.4 | |
| GPT-4.1Size=Large, Strategy Selection=All2026.03 | 48.6 | 46.9 | 30.3 | 272.727 | 5.1 | |
| Qwen3-8BSize=Small, Strategy Selection=All2026.03 | 48.3 | 46.8 | 28.4 | 146.626 | 19.7 | |
| GPT-4.1-MiniSize=Large, Strategy Selection=All2026.03 | 47.6 | 45.7 | 30.6 | 211.039 | 26.4 | |
| Qwen2.5-Coder-7BSize=Small, Strategy Selection=All2026.03 | 47.6 | 36.1 | 20.8 | 136.469 | 17.8 | |
| GPT-4.1Size=Large, Strategy Selection=Top2026.03 | 47.5 | 47.5 | 33.9 | 261.203 | 12.4 | |
| Qwen2.5-Coder-7BSize=Small, Strategy Selection=Top2026.03 | 46.4 | 37.1 | 21.9 | 151.447 | 12.2 | |
| LLaMA-3.1-8BSize=Small, Strategy Selection=All2026.03 | 42 | 35.9 | 19 | 12.43 | -1.8 | |
| LLaMA-3.1-8BSize=Small, Strategy Selection=Top2026.03 | 41.6 | 37.1 | 20.8 | 2.734 | 11.8 | |
| Qwen3-4BSize=Small, Strategy Selection=All2026.03 | 41 | 40 | 17.9 | 118.627 | -0.4 | |
| Qwen3-4BSize=Small, Strategy Selection=Top2026.03 | 40.6 | 42 | 21.7 | 140.538 | 0 |