List your company

Correctness simulation accuracy on DBE-KT22 20% historical interaction logs

69.9AccuracyEdu-Theater
54.726458.665762.60566.5443Jun 13, 2026

Evaluation results

MethodLinks
Edu-TheaterBase LLM=GPT-4.1-mini2026.0669.9
Agent4EduBase LLM=GPT-4.1-mini2026.0669.32
EERNN2026.0668.53
EduAgentBase LLM=GPT-4.1-mini2026.0668.42
SAKT2026.0667.88
Edu-TheaterBase LLM=Llama3-8b2026.0666.33
Agent4EduBase LLM=Llama3-8b2026.0666.02
EduAgentBase LLM=Llama3-8b2026.0665.67
DAISIM2026.0665.25
DKVMN2026.0660.14
KES2026.0655.31