Causal Discovery on Multitasking Behaviour (test)
50ACCGemini-deepresearch
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Gemini-deepresearch2026.02 | 50 | 65.7 | 38.3 | |
| TLVD2026.02 | 50 | 82 | 28.3 | |
| OpenAI-deepresearch2026.02 | 35 | 15 | 15 | |
| GPT52026.02 | 25 | 8.3 | 8.3 | |
| MiniMax2026.02 | 15 | 0 | 0 | |
| Multi-Agent-Majority2026.02 | 10 | 16.7 | 8.3 | |
| Qwen-deepresearch2026.02 | 5 | 0 | 0 | |
| Autogen2026.02 | 5 | 0 | 0 | |
| CAMEL2026.02 | 5 | 0 | 0 | |
| Doubao-deepresearch2026.02 | 0 | 0 | 0 | |
| Multi-Agent Debate2026.02 | 0 | 0 | 0 |