List your company

Long-form Dialogue on SCM4LLMs

91.08QualityDYCP
53.84863.51473.1882.846Jan 12, 2026

Evaluation results

MethodLinks
DYCPAgent=GPT-4.12026.0191.080.77
Full ContextAgent=GPT-4.12026.0190.831.91
DYCPAgent=Claude 3.72026.0188.922.52
DYCPAgent=Claude 4.02026.0188.191.79
Full ContextAgent=Claude 3.72026.0188.086.3
DYCPAgent=GPT-4o2026.0187.571.03
SeComAgent=Claude 3.72026.0186.323.54
Full ContextAgent=GPT-4o2026.0185.512.06
SeComAgent=GPT-4o2026.0185.40.79
Full ContextAgent=Claude 4.02026.0184.893.25
DYCPAgent=GPT-4o mini2026.0184.550.99
SCM4LLMsAgent=GPT-4o mini2026.0184.384.22
MemoChatAgent=GPT-4o2026.0183.473.52
SeComAgent=GPT-4o mini2026.0183.090.74
Full ContextAgent=GPT-4o mini2026.0183.081.63
DYCPAgent=Mistral-Nemo-Instruct (128k)2026.0180.681.15
SCM4LLMsAgent=Claude 3.72026.0179.567.82
MemoChatAgent=Claude 3.72026.0178.497.48
MemoChatAgent=GPT-4o mini2026.0178.423.24
SCM4LLMsAgent=GPT-4o2026.0176.113.43
DYCPAgent=Qwen2.5-7B-Instruct (1M)2026.0175.620.77
Full ContextAgent=Qwen2.5-7B-Instruct (1M)2026.0174.924.41
Full ContextAgent=Mistral-Nemo-Instruct (128k)2026.0171.067.3
CondMemAgent=Mistral-Nemo-Instruct (128k)2026.0165.15.57
No ContextAgent=GPT-4.12026.0162.410.43
CondMemAgent=Qwen2.5-7B-Instruct (1M)2026.0160.0810.36
No ContextAgent=GPT-4o mini2026.0159.620.53
No ContextAgent=Qwen2.5-7B-Instruct (1M)2026.0158.570.05
No ContextAgent=GPT-4o2026.0158.470.45
No ContextAgent=Claude 3.72026.0157.91.57
No ContextAgent=Claude 4.02026.0157.891.57
No ContextAgent=Mistral-Nemo-Instruct (128k)2026.0155.280.07