DeepResearch Bench - Citation Accuracy: leaderboard
The "Citation Accuracy" subtask of DeepResearch Bench. Benchmark for deep research agents, evaluating long-form research reports across comprehensiveness, insight, instruction following, readability, and citation quality.
Metric: Score (%). Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.7 Sonnet | 87.32 | #249 |
| 2 | GPT-4o Search Preview | 86.63 | #455 |
| 3 | Sonar Pro | 79.72 | #269 |
| 4 | Gemini 2.5 Pro | 78.3 | #152 |
| 5 | Doubao Deep Research | 52.86 | #182 |
Interactive version: theaggregate.ai/benchmark?slug=deepresearch-bench-citation-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-20.