Instruction Following Evaluation on LMSYS In-Dist.
51.8GPT-4o ScoreSODA
Evaluation results
| Method | Links | |
|---|---|---|
| SODAModel=Llama-3.1-8B-Instruct2026.04 | 51.8 | |
| TeacherModel=GPT-5-Chat2026.04 | 51.7 | |
| SODAModel=Qwen2.5-7B-Instruct2026.04 | 51.5 | |
| GADModel=Qwen2.5-7B-Instruct2026.04 | 50.8 | |
| GADModel=Llama-3.1-8B-Instruct2026.04 | 50.3 | |
| SeqKDModel=Llama-3.1-8B-Instruct2026.04 | 49.7 | |
| SODAModel=Qwen2.5-3B-Instruct2026.04 | 49.2 | |
| SeqKDModel=Qwen2.5-7B-Instruct2026.04 | 49.2 | |
| SODAModel=Llama-3.2-3B-Instruct2026.04 | 49.1 | |
| GADModel=Qwen2.5-3B-Instruct2026.04 | 48.9 | |
| BaseModel=Qwen2.5-7B-Instruct2026.04 | 48.7 | |
| GADModel=Llama-3.2-3B-Instruct2026.04 | 48.1 | |
| SeqKDModel=Llama-3.2-3B-Instruct2026.04 | 47.6 | |
| SeqKDModel=Qwen2.5-3B-Instruct2026.04 | 47.5 | |
| BaseModel=Llama-3.1-8B-Instruct2026.04 | 46.9 | |
| BaseModel=Qwen2.5-3B-Instruct2026.04 | 45.8 | |
| BaseModel=Llama-3.2-3B-Instruct2026.04 | 44 |