Instruction Following on FollowBench In-Domain
70.4HSRGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4oBase Model=GPT2025.10 | 70.4 | |
| Qwen2.5-32B-Instruct-IFBase Model=Qwen-32B2025.10 | 66.8 | |
| Qwen2.5-32B-InstructBase Model=Qwen-32B2025.10 | 65.1 | |
| R1-0528-Qwen3-8BBase Model=Qwen-8B2025.10 | 63.8 | |
| QwQ-32BBase Model=Qwen-32B2025.10 | 62.2 | |
| R1-0528-Qwen3-8BBase Model=Qwen-8B2025.10 | 60.4 | |
| Distill-Qwen-14B-IFBase Model=Qwen-14B2025.10 | 57.6 | |
| Qwen2.5-7B-Instruct-IFBase Model=Qwen-7B2025.10 | 57.5 | |
| Llama-3.1-8B-Instruct-IFBase Model=LLaMA-8B2025.10 | 57.5 | |
| VERIF-8BBase Model=LLaMA-8B2025.10 | 56.9 | |
| SPAR-8B-DPOBase Model=LLaMA-8B2025.10 | 56.1 | |
| Qwen2.5-7B-InstructBase Model=Qwen-7B2025.10 | 55.1 | |
| Llama-3.1-8B-InstructBase Model=LLaMA-8B2025.10 | 53.8 | |
| Distill-Qwen-14BBase Model=Qwen-14B2025.10 | 51.2 | |
| Conifer-7B-DPOBase Model=Mistral-7B2025.10 | 50 | |
| Crab-7B-DPOBase Model=Mistral-7B2025.10 | 49.4 | |
| Distill-Qwen-7B-IFBase Model=Qwen-7B2025.10 | 49.1 | |
| Distill-Qwen-7BBase Model=Qwen-7B2025.10 | 41.7 | |
| Qwen2.5-1.5B-Instruct-IFBase Model=Qwen-1.5B2025.10 | 39 | |
| IR-1.5BBase Model=Qwen-1.5B2025.10 | 37.8 | |
| Qwen2.5-1.5B-InstructBase Model=Qwen-1.5B2025.10 | 34.6 | |
| Distill-Qwen-1.5B-IFBase Model=Qwen-1.5B2025.10 | 26.4 | |
| Distill-Qwen-1.5BBase Model=Qwen-1.5B2025.10 | 22.7 |