Instruction Following on IFEval In-Domain
0.871Precision (L)VERIF-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| VERIF-8BBase Model=LLaMA-8B2025.10 | 0.871 | |
| R1-0528-Qwen3-8BBase Model=Qwen-8B2025.10 | 0.871 | |
| Qwen2.5-32B-Instruct-IFBase Model=Qwen-32B2025.10 | 0.85 | |
| GPT-4oBase Model=GPT2025.10 | 0.848 | |
| QwQ-32BBase Model=Qwen-32B2025.10 | 0.839 | |
| Distill-Qwen-14B-IFBase Model=Qwen-14B2025.10 | 0.837 | |
| Llama-3.1-8B-Instruct-IFBase Model=LLaMA-8B2025.10 | 0.83 | |
| SPAR-8B-DPOBase Model=LLaMA-8B2025.10 | 0.824 | |
| Qwen2.5-32B-InstructBase Model=Qwen-32B2025.10 | 0.824 | |
| R1-0528-Qwen3-8BBase Model=Qwen-8B2025.10 | 0.797 | |
| Qwen2.5-7B-Instruct-IFBase Model=Qwen-7B2025.10 | 0.789 | |
| Distill-Qwen-14BBase Model=Qwen-14B2025.10 | 0.749 | |
| Qwen2.5-7B-InstructBase Model=Qwen-7B2025.10 | 0.739 | |
| Llama-3.1-8B-InstructBase Model=LLaMA-8B2025.10 | 0.738 | |
| Distill-Qwen-7B-IFBase Model=Qwen-7B2025.10 | 0.717 | |
| Qwen2.5-1.5B-Instruct-IFBase Model=Qwen-1.5B2025.10 | 0.652 | |
| Distill-Qwen-7BBase Model=Qwen-7B2025.10 | 0.617 | |
| Distill-Qwen-1.5B-IFBase Model=Qwen-1.5B2025.10 | 0.588 | |
| IR-1.5BBase Model=Qwen-1.5B2025.10 | 0.577 | |
| Crab-7B-DPOBase Model=Mistral-7B2025.10 | 0.577 | |
| Conifer-7B-DPOBase Model=Mistral-7B2025.10 | 0.523 | |
| Qwen2.5-1.5B-InstructBase Model=Qwen-1.5B2025.10 | 0.436 | |
| Distill-Qwen-1.5BBase Model=Qwen-1.5B2025.10 | 0.423 |