Reasoning and Knowledge Assessment on Xstorycloze bo
72.96AccuracyOurs-MoE-SFT
Evaluation Results
| Method | Links | |
|---|---|---|
| Ours-MoE-SFTModel=Ours-MoE-SFT2025.07 | 72.96 | |
| Ours-SFTModel=Ours-SFT2025.07 | 61.86 | |
| Ours-MoE-Base-8kModel=Ours-MoE-Base-8k2025.07 | 60.86 | |
| Ours-BaseModel=Ours-Base2025.07 | 60.8 | |
| Ours-MoE-BaseModel=Ours-MoE-Base2025.07 | 60.74 | |
| Ours-Base-32kModel=Ours-Base-32k2025.07 | 60.6 | |
| LLaMA3.1-8B-InstructModel=LLaMA3.1-8B-Instruct2025.07 | 51.69 | |
| Qwen2.5-7B-InstructModel=Qwen2.5-7B-Instruct2025.07 | 50.43 | |
| Qwen3-8BModel=Qwen3-8B2025.07 | 50.37 | |
| Qwen2.5-7B-baseModel=Qwen2.5-7B-base2025.07 | 49.97 | |
| DeepSeek-R1-Distill-Llama-8BModel=DeepSeek-R1-Distill-Llama-8B2025.07 | 48.5 |