Instruction-following clustering on ECHR (C2)
66.39V-measureC1-Qwen-14B
Evaluation Results
| Method | Links | |
|---|---|---|
| C1-Qwen-14BModel Type=Our Model2026.03 | 66.39 | |
| Gemini 2.5 ProModel Type=Reasoning Model2026.03 | 64.29 | |
| Distill-Llama-70BModel Type=Reasoning Model2026.03 | 57.79 | |
| QwQ-32BModel Type=Reasoning Model2026.03 | 56.68 | |
| GPT-4oModel Type=General Model2026.03 | 52.86 | |
| C1-Qwen-7BModel Type=Our Model2026.03 | 52.66 | |
| GPT-oss-120BModel Type=Reasoning Model2026.03 | 52.58 | |
| Qwen2.5-72B-InstructModel Type=General Model2026.03 | 51.77 | |
| o3Model Type=Reasoning Model2026.03 | 47.04 | |
| Distill-Qwen-32BModel Type=Reasoning Model2026.03 | 44.04 | |
| GPT-4.1Model Type=General Model2026.03 | 40.05 | |
| Llama-3.1-70B-InstructModel Type=General Model2026.03 | 35.77 | |
| DeepSeek-R1Model Type=Reasoning Model2026.03 | 34.06 |