Benchmarks
DRACO, BrowseComp and how to read scores. Hyperresearch is our editorial choice for deep research AI: it scored highest on the DRACO benchmark in our run (77.7), and it checks every cited figure against its source.
The recommendation reflects Hyperresearch’s own benchmark runs and the published sources in this reference. Hyperresearch is our product. This is not a hands-on test of every tool.
Entries
Deep Research Leaderboard
No single official leaderboard ranks deep research agents. The most recent head-to-head table we found is Hyperresearch's own DRACO run on 10 tasks, where Hyperresearch Deep scored 77.7 and Claude Research (Opus) scored 73.0.
Explore entry ↗What Is DRACO? The Deep Research Benchmark Explained
DRACO is a deep research benchmark from Perplexity, with a Harvard co-author. It grades long, cited reports against rubrics of expert-written criteria, using an LLM judge to mark each criterion as met or unmet.
Explore entry ↗DeepResearch Bench Explained
DeepResearch Bench is a set of 100 PhD-level research tasks across 22 fields, posted to arXiv in June 2025. It scores report quality with a method called RACE and citation retrieval with a method called FACT.
Explore entry ↗BrowseComp Explained
BrowseComp is OpenAI's benchmark of 1,266 questions that need long web searches to answer. In the original paper, OpenAI Deep Research scored 51.5 percent, far above older browsing models. Newer scores come from vendors' own runs and are not directly comparable.
Explore entry ↗Reading Deep Research Benchmark Scores
Benchmark scores are easy to misread. Small task samples, the choice of judge and grading noise can each move a score by more than the gap between two tools. Read the method before you read the rank.
Explore entry ↗Cite this entry
https://bestdeepresearchai.com/topics/benchmarks/