List your company

Instruction-following clustering on ECHR (C0)

85.75V-measureo3
40.967652.593864.2275.8462Mar 6, 2026

Evaluation results

MethodLinks
o3Model Type=Reasoning Model2026.0385.75
Gemini 2.5 ProModel Type=Reasoning Model2026.0385.05
C1-Qwen-14BModel Type=Our Model2026.0384.05
C1-Qwen-7BModel Type=Our Model2026.0381.81
QwQ-32BModel Type=Reasoning Model2026.0375.98
GPT-oss-120BModel Type=Reasoning Model2026.0370.54
GPT-4.1Model Type=General Model2026.0364.93
Distill-Llama-70BModel Type=Reasoning Model2026.0363.45
GPT-4oModel Type=General Model2026.0358.86
Distill-Qwen-32BModel Type=Reasoning Model2026.0354.43
DeepSeek-R1Model Type=Reasoning Model2026.0353.78
Qwen2.5-72B-InstructModel Type=General Model2026.0345.57
Llama-3.1-70B-InstructModel Type=General Model2026.0342.69