ResearcherBench — leaderboard

Evaluates deep AI research systems on producing comprehensive research reports, measuring coverage of key insights, faithfulness to sources, and groundedness of claims.

Metric: Coverage (%). Source: github.com. 10 models tracked.

Top models

#ModelScore
1OpenAI Deep Research70.3
2Gemini Deep Research69.3
3Claude Research61.1
4Mita Deep Research58.4
5Doubao Deep Research57.5
6Perplexity Deep Research48
7Perplexity: Sonar Reasoning Pro46.6
8Grok3 DeepSearch44.1
9Grok3 DeeperSearch44
10GPT-4o Search Preview35.8

Interactive version: theaggregate.ai/benchmark?slug=researcherbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.