Instruction-following clustering on LMSY (C1)
66.47V-measureC1-Qwen-14B
Evaluation Results
| Method | Links | |
|---|---|---|
| C1-Qwen-14BModel Type=Our Model2026.03 | 66.47 | |
| C1-Qwen-7BModel Type=Our Model2026.03 | 65.04 | |
| o3Model Type=Reasoning Model2026.03 | 63.42 | |
| Gemini 2.5 ProModel Type=Reasoning Model2026.03 | 56.06 | |
| GPT-oss-120BModel Type=Reasoning Model2026.03 | 49.3 | |
| QwQ-32BModel Type=Reasoning Model2026.03 | 48.84 | |
| DeepSeek-R1Model Type=Reasoning Model2026.03 | 43.64 | |
| GPT-4.1Model Type=General Model2026.03 | 39.99 | |
| Distill-Llama-70BModel Type=Reasoning Model2026.03 | 39.04 | |
| GPT-4oModel Type=General Model2026.03 | 30.15 | |
| Distill-Qwen-32BModel Type=Reasoning Model2026.03 | 27.89 | |
| Llama-3.1-70B-InstructModel Type=General Model2026.03 | 27.5 | |
| Qwen2.5-72B-InstructModel Type=General Model2026.03 | 20.08 |