Causal Discovery on Teacher's Burnout Study (test)
58.2AccuracyTLVD
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| TLVD2026.02 | 58.2 | 76.9 | 35.7 | |
| OpenAI-deepresearch2026.02 | 56.4 | 76.2 | 35.4 | |
| Gemini-deepresearch2026.02 | 36.4 | 31.5 | 14.6 | |
| MiniMax2026.02 | 32.7 | 30 | 13.9 | |
| Multi-Agent Debate2026.02 | 29.1 | 16.2 | 7.5 | |
| Multi-Agent-Majority2026.02 | 27.3 | 18.5 | 8.6 | |
| Autogen2026.02 | 25.5 | 20.8 | 9.6 | |
| CAMEL2026.02 | 23.6 | 19.2 | 8.9 | |
| Qwen-deepresearch2026.02 | 16.4 | 15.4 | 7.1 | |
| GPT52026.02 | 14.5 | 6.9 | 3.2 | |
| Doubao-deepresearch2026.02 | 12.7 | 13.1 | 6.1 |