List your company

Correctness simulation accuracy on DBE-KT22 30% historical interaction logs

70.33AccuracyEdu-Theater
59.72262.47665.2367.984Jun 13, 2026

Evaluation results

MethodLinks
Edu-TheaterBase LLM=GPT-4.1-mini2026.0670.33
Agent4EduBase LLM=GPT-4.1-mini2026.0669.43
Edu-TheaterBase LLM=Llama3-8b2026.0668.67
EduAgentBase LLM=GPT-4.1-mini2026.0668.57
EERNN2026.0668.35
Agent4EduBase LLM=Llama3-8b2026.0668.3
SAKT2026.0667.92
DAISIM2026.0666.33
EduAgentBase LLM=Llama3-8b2026.0665.3
DKVMN2026.0664.32
KES2026.0660.13