Search leaderboard
DeepSearchQA
Deep, multi-step research with complete answers.
Scores are temporarily unavailable. Please check back shortly.
What it measures
Multi-step information-seeking tasks across many fields, where the answer is often a set of items rather than a single fact. Agents are scored on finding a complete and precise answer with web search enabled.
Beyond public benchmarks
Get a private eval built for your model.
Deep research quality is hard to grade automatically. Our experts write rubric-graded research tasks and judge completeness the way your users would.
- Unpublished tasks written by vetted US-based subject-matter experts
- Rubric-based grading with expert review, not just automated scoring
- Delivered under NDA, with training data to close the gaps it finds
More leaderboards
Search
BrowseComp
Search
Humanity’s Last Exam
Search
WideSearch
Reasoning
GPQA Diamond
Agentic
Tau-Bench Airline
Design Arena / App Building
Full-Stack Apps
Design Arena / App Building
Web Apps
Design Arena / App Building
Mobile Apps
Design Arena / App Building
Native Android
Design Arena / App Building
Godot Game Dev
Design Arena / Design
Websites
Design Arena / Design
UI Components
Design Arena / Design
Game Dev
Design Arena / Design
3D
Design Arena / Design
Data Visualization
Design Arena / Design