List your company

Service Dialogue Task on Service dialogue scenarios

52CRSEAD
30.78436.29241.847.308Feb 3, 2026

Evaluation results

MethodLinks
SEADParams=14B2026.02529.60.9120.631.571.550
GPT-4o2026.0244.210.80.8670.040.971.34727.28
LongCat-FlashParams=560B2026.0242.2100.9250.281.331.5623.08
Qwen2.5-72B-InstructParams=72B2026.02399.60.8180.511.061.180
Qwen2.5-14B-InstructParams=14B2026.0238.710.50.8830.340.680.630
Qwen2.5-32B-InstructParams=32B2026.0238.39.90.899-0.110.762.250
Qwen3-235BParams=235B2026.0232.310.40.765-0.240.81.5469.36
DeepSeek-ChatParams=671B2026.0231.611.30.863-0.20.270.7687.36