Biomedical Evidence Synthesis on MDD (Major Depressive Disorder)
4Automatic Coverage ScoreGemini Deep Search
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Gemini Deep SearchSearch configuration=Deep Research, Model type=Commercial deep-research workflow2026.06 | 4 | 3 | 2.5 | 3.5 | 4.5 | 4.5 | 3.5 | 4.5 | 4.5 | |
| BioInsightSearch configuration=+ Search, Reasoning stages=Full system2026.06 | 4 | 4 | 3.5 | 4 | 3.67 | 3 | 3 | 3.33 | 4.5 | |
| GPT5.5 + WebSearch configuration=+ Web, Model type=Frontier search-enabled2026.06 | 3.5 | 4 | 3.5 | 4 | 4.33 | 4.67 | 4.33 | 3.67 | 4.33 | |
| BioInsight (w/o Search)Search configuration=w/o Search, Reasoning stages=Ablated2026.06 | 3.5 | 3 | 2.5 | 3 | — | — | — | — | — | |
| Qwen3.5-9BSearch configuration=+ Search, Model type=Open-weight2026.06 | 3 | 3 | 2.5 | 3 | — | — | — | — | — | |
| DR-Tulu-8BSearch configuration=+ Search, Model type=Biomedical/domain-oriented2026.06 | 2.5 | 2.5 | 1.5 | 2 | 3 | 2.33 | 3.33 | 2.33 | 2 |