Multiple-choice Question Answering on CFA
58.34Accuracy (%)DS2-INSTRUCT
Evaluation Results
| Method | Links | |
|---|---|---|
| DS2-INSTRUCTModel Family=Qwen2.52026.03 | 58.34 | |
| InstructMixModel Family=Qwen2.52026.03 | 57.91 | |
| DS2-INSTRUCTModel Family=Llama32026.03 | 56.94 | |
| ExploreInstructModel Family=Qwen2.52026.03 | 56.47 | |
| Self-InstructModel Family=Qwen2.52026.03 | 55.83 | |
| DS2-INSTRUCTModel Family=Mistral2026.03 | 55.72 | |
| Zero-ShotModel Family=Qwen2.52026.03 | 53.71 | |
| InstructMixModel Family=Mistral2026.03 | 42.15 | |
| ExploreInstructModel Family=Mistral2026.03 | 38.64 | |
| InstructMixModel Family=Llama32026.03 | 36.89 | |
| ExploreInstructModel Family=Llama32026.03 | 34.58 | |
| Self-InstructModel Family=Llama32026.03 | 33.72 | |
| Self-InstructModel Family=Mistral2026.03 | 14.26 | |
| Zero-ShotModel Family=Llama32026.03 | 9.76 | |
| Zero-ShotModel Family=Mistral2026.03 | 4.61 |