Instruction-following clustering on ECHR (C1)
85.79V-measureo3
Evaluation Results
| Method | Links | |
|---|---|---|
| o3Model Type=Reasoning Model2026.03 | 85.79 | |
| C1-Qwen-14BModel Type=Our Model2026.03 | 84.8 | |
| Gemini 2.5 ProModel Type=Reasoning Model2026.03 | 84.14 | |
| C1-Qwen-7BModel Type=Our Model2026.03 | 82.76 | |
| QwQ-32BModel Type=Reasoning Model2026.03 | 72.63 | |
| GPT-oss-120BModel Type=Reasoning Model2026.03 | 69.18 | |
| Distill-Llama-70BModel Type=Reasoning Model2026.03 | 66.4 | |
| GPT-4.1Model Type=General Model2026.03 | 59.87 | |
| GPT-4oModel Type=General Model2026.03 | 56.15 | |
| DeepSeek-R1Model Type=Reasoning Model2026.03 | 54.55 | |
| Distill-Qwen-32BModel Type=Reasoning Model2026.03 | 53.15 | |
| Llama-3.1-70B-InstructModel Type=General Model2026.03 | 44.58 | |
| Qwen2.5-72B-InstructModel Type=General Model2026.03 | 44.03 |