DeepResearch Bench - Effective Citations: leaderboard
The "Effective Citations" subtask of DeepResearch Bench. Benchmark for deep research agents, evaluating long-form research reports across comprehensiveness, insight, instruction following, readability, and citation quality.
Metric: Effective Citations. Source: huggingface.co. Saturation forecast: Estimated already saturated. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 165.34 | #152 |
| 2 | Doubao Deep Research | 52.62 | #182 |
| 3 | Claude 3.7 Sonnet | 24.51 | #249 |
| 4 | Sonar Pro | 16.75 | #269 |
| 5 | GPT-4o Search Preview | 5.05 | #455 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=deepresearch-bench-effective-citations · How It Works · Data refreshed daily, snapshot 2026-10-20.