Sentiment Analysis on FPB (Weighted F1, AVG)
0.911Weighted F1FinMA-7B-full
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FinMA-7B-fullDomain Focus=Financial2026.03 | 0.911 | — | |
| ODA-Fin-RL-8BDomain Focus=Financial2026.03 | 0.834 | 0.746 | |
| Gemini 2.5 Flash-LiteReasoning Capability=with Reasoning, Domain Focus=General2026.03 | 0.798 | 0.677 | |
| Qwen2.5-7B-InstructReasoning Capability=without Reasoning, Domain Focus=General2026.03 | 0.786 | 0.68 | |
| Qwen3-32BReasoning Capability=without Reasoning, Domain Focus=General2026.03 | 0.773 | 0.747 | |
| GPT-5 mini-highReasoning Capability=with Reasoning, Domain Focus=General2026.03 | 0.77 | 0.771 | |
| Qwen3-8BReasoning Capability=without Reasoning, Domain Focus=General2026.03 | 0.768 | 0.715 | |
| Dianjin-R1-7BDomain Focus=Financial2026.03 | 0.764 | 0.703 | |
| ODA-Fin-SFT-8BDomain Focus=Financial2026.03 | 0.756 | 0.721 | |
| Llama-3.1-8B-InstructReasoning Capability=without Reasoning, Domain Focus=General2026.03 | 0.731 | 0.569 | |
| Qwen3-4B-ThinkingReasoning Capability=with Reasoning, Domain Focus=General2026.03 | 0.702 | 0.725 | |
| Plutus-8B-InstructDomain Focus=Financial2026.03 | 0.667 | 0.362 | |
| Xuanyuan-6B-ChatDomain Focus=Financial2026.03 | 0.655 | 0.367 | |
| Qwen2.5-7BReasoning Capability=without Reasoning, Domain Focus=General2026.03 | 0.599 | 0.478 | |
| Fin-R1Domain Focus=Financial2026.03 | 0.271 | 0.614 |