Learner Answer Simulation on DBE-KT22
69.4AccuracyEdu-Theater
Evaluation Results
| Method | Links | |
|---|---|---|
| Edu-TheaterBackbone LLM=GPT-4.1-mini2026.06 | 69.4 | |
| Edu-TheaterBackbone LLM=GPT-4o2026.06 | 68.6 | |
| Agent4EduBackbone LLM=GPT-4.1-mini2026.06 | 67.4 | |
| Edu-TheaterBackbone LLM=GPT-3.5-turbo2026.06 | 67.1 | |
| Agent4EduBackbone LLM=GPT-4o2026.06 | 66.9 | |
| EduAgentBackbone LLM=GPT-4.1-mini2026.06 | 65.9 | |
| Edu-TheaterBackbone LLM=Llama3-8b2026.06 | 65.8 | |
| EduAgentBackbone LLM=GPT-4o2026.06 | 65.3 | |
| Edu-TheaterBackbone LLM=Llama2-7b2026.06 | 65.2 | |
| Agent4EduBackbone LLM=GPT-3.5-turbo2026.06 | 64.8 | |
| Agent4EduBackbone LLM=Llama3-8b2026.06 | 64.1 | |
| Agent4EduBackbone LLM=Llama2-7b2026.06 | 63.8 | |
| EduAgentBackbone LLM=GPT-3.5-turbo2026.06 | 63.2 | |
| EduAgentBackbone LLM=Llama3-8b2026.06 | 62.3 | |
| EduAgentBackbone LLM=Llama2-7b2026.06 | 61.9 | |
| Llama3-8b2026.06 | 59.4 | |
| GPT-4.1-mini2026.06 | 58.1 | |
| GPT-3.5-turbo2026.06 | 57.6 |