Instruction-following clustering on LMSY (C2)
64.17V-measureo3
Evaluation Results
| Method | Links | |
|---|---|---|
| o3Model Type=Reasoning Model2026.03 | 64.17 | |
| C1-Qwen-14BModel Type=Our Model2026.03 | 62.65 | |
| C1-Qwen-7BModel Type=Our Model2026.03 | 58.51 | |
| Gemini 2.5 ProModel Type=Reasoning Model2026.03 | 57.95 | |
| QwQ-32BModel Type=Reasoning Model2026.03 | 53.74 | |
| GPT-oss-120BModel Type=Reasoning Model2026.03 | 52.77 | |
| Distill-Llama-70BModel Type=Reasoning Model2026.03 | 47.76 | |
| DeepSeek-R1Model Type=Reasoning Model2026.03 | 45.8 | |
| GPT-4.1Model Type=General Model2026.03 | 43.42 | |
| Distill-Qwen-32BModel Type=Reasoning Model2026.03 | 39.45 | |
| GPT-4oModel Type=General Model2026.03 | 33.38 | |
| Llama-3.1-70B-InstructModel Type=General Model2026.03 | 28.97 | |
| Qwen2.5-72B-InstructModel Type=General Model2026.03 | 27.78 |