Causal Discovery on WCHSU-Cancer original (test)
75ACCTLVD
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| TLVD2026.02 | 75 | 92 | 32.9 | |
| OpenAI-deepresearch2026.02 | 55 | 21.4 | 21.4 | |
| Autogen2026.02 | 45 | 25.5 | 20 | |
| CAMEL2026.02 | 40 | 0 | 0 | |
| Multi-Agent Debate2026.02 | 35 | 0 | 0 | |
| Gemini-deepresearch2026.02 | 30 | 34.7 | 23.6 | |
| MiniMax2026.02 | 30 | 19.2 | 17.1 | |
| Qwen-deepresearch2026.02 | 25 | 27.1 | 27.1 | |
| Multi-Agent-Majority2026.02 | 20 | 0 | 0 | |
| GPT52026.02 | 15 | 11.6 | 7.9 | |
| Doubao-deepresearch2026.02 | 0 | 0 | 0 |