Financial Question Answering on S&P 500 benchmark
56.78Forecast QA ScoreSTOCK-R1-8B
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| STOCK-R1-8BModel Category=Financial LLM, Model Size=8B, Base Model=Qwen3-8B2026.05 | 56.78 | 67.49 | 61.08 | 67.16 | 67.45 | 63.99 | |
| STOCK-R1-4BModel Category=Financial LLM, Model Size=4B, Base Model=Qwen3-4B2026.05 | 51 | 68.52 | 59.7 | 61.83 | 63.02 | 60.81 | |
| Fin-R1-8BModel Category=Financial LLM, Model Size=8B2026.05 | 40.28 | 49.35 | 56.41 | 60.48 | 60.28 | 53.36 | |
| DianJin-R1-32BModel Category=Financial LLM, Model Size=32B2026.05 | 38.42 | 63.71 | 52.47 | 62.4 | 62.58 | 55.92 | |
| Fin-o1-14BModel Category=Financial LLM, Model Size=14B2026.05 | 32.86 | 31.89 | 41.27 | 53.53 | 69.12 | 45.73 | |
| Qwen3-30BModel Category=General-purpose LLM, Model Size=30B2026.05 | 10.34 | 55.35 | 45.4 | 51.41 | 63.39 | 45.18 | |
| GPT-5Model Category=General-purpose LLM2026.05 | 8.16 | 51.08 | 52.69 | 60.49 | 61.24 | 46.73 | |
| Qwen3-4BModel Category=General-purpose LLM, Model Size=4B2026.05 | 7.92 | 65.58 | 48.94 | 35.11 | 57.82 | 43.07 | |
| Qwen3-8BModel Category=General-purpose LLM, Model Size=8B2026.05 | 6.23 | 39.42 | 47.06 | 44.79 | 52.69 | 38.04 | |
| Llama3-70BModel Category=General-purpose LLM, Model Size=70B2026.05 | 5.35 | 53.25 | 59.34 | 55.28 | 60.85 | 46.81 | |
| DeepSeek-V3.2Model Category=General-purpose LLM2026.05 | 3.37 | 56.9 | 44.58 | 42 | 60.95 | 41.56 | |
| Llama3-8BModel Category=General-purpose LLM, Model Size=8B2026.05 | 3.21 | 44.1 | 47.13 | 51.77 | 54.81 | 40.2 | |
| OpenAI-o3Model Category=General-purpose LLM2026.05 | 2.78 | 53.43 | 57.76 | 57.89 | 67.07 | 47.79 | |
| Llama3-3BModel Category=General-purpose LLM, Model Size=3B2026.05 | 2.53 | 48.87 | 45.68 | 42.72 | 56.54 | 39.27 |