Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Correctness simulation accuracy on DBE-KT22 50% historical interaction logs
Loading...
71.27
Accuracy
Edu-Theater
62.95
65.11
67.27
69.43
Jun 13, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Edu-Theater
Base LLM=GPT-4.1-mini
2026.06
71.27
Agent4Edu
Base LLM=GPT-4.1-mini
2026.06
69.95
Edu-Theater
Base LLM=Llama3-8b
2026.06
69.67
Agent4Edu
Base LLM=Llama3-8b
2026.06
69.63
EERNN
2026.06
69.04
EduAgent
Base LLM=GPT-4.1-mini
2026.06
68.52
DAISIM
2026.06
68.44
SAKT
2026.06
68.37
EduAgent
Base LLM=Llama3-8b
2026.06
67.33
DKVMN
2026.06
65.33
KES
2026.06
63.27
Feedback
Search any
task
Search any
task