Stock trading on HON (test)
43.944Calmar Ratio (%)Llama-3.1-70B-Instruct
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Llama-3.1-70B-InstructModel Category=Open-Source Models2025.02 | 43.944 | 2.646 | 27.903 | 8.993 | |
| Llama-3.1-8B-InstructModel Category=Open-Source Models2025.02 | 39.079 | 2.32 | 28.299 | 10.341 | |
| GPT-4oModel Category=Proprietary Models2025.02 | 38.54 | 2.418 | 26.782 | 8.979 | |
| GPT-4Model Category=Proprietary Models2025.02 | 34.342 | 2.005 | 28.779 | 9.195 | |
| FLAG-TRADERBackbone=SmolLM2-135M-Instruct2025.02 | 34.342 | 2.429 | 23.913 | 10.872 | |
| Qwen2.5-72B-InstructModel Category=Open-Source Models2025.02 | 34.309 | 2 | 28.779 | 9.292 | |
| Buy & HoldModel Category=Baseline2025.02 | 33.256 | 2.347 | 23.967 | 9.195 | |
| DeepSeek-67B-ChatModel Category=Open-Source Models2025.02 | 32.536 | 1.909 | 28.628 | 10.782 | |
| Yi-1.5-34B-ChatModel Category=Open-Source Models2025.02 | 30.743 | 1.823 | 28.335 | 9.195 | |
| Yi-1.5-9B-ChatModel Category=Open-Source Models2025.02 | 29.028 | 1.7 | 28.682 | 12.588 | |
| Qwen2.5-32B-InstructModel Category=Open-Source Models2025.02 | 26.332 | 1.98 | 22.348 | 5.261 | |
| Palmyra-Fin-70BModel Category=Financial Domain Models2025.02 | 20.016 | 1.464 | 22.974 | 6.824 | |
| DeepSeek-V2-Lite (15.7B)Model Category=Open-Source Models2025.02 | 16.686 | 0.974 | 28.771 | 16.806 | |
| GPT-o1-previewModel Category=Proprietary Models2025.02 | 13.162 | 0.776 | 28.511 | 11.558 | |
| Qwen-2.5-Instruct-7BModel Category=Open-Source Models2025.02 | 4.291 | 0.285 | 24.933 | 14.156 |