⌘K
Toggle Sidebar
⌘K
Frontier Leaderboards
Humanity's Last Exam
Humanity's Last Exam (Text Only)
MultiNRC
MultiChallenge
Fortress
MASK
EnigmaEval
VISTA
Legacy Leaderboards
Humanity's Last Exam Text Only (Preview)
Humanity's Last Exam (Preview)
Chinese
Arabic
Korean
Japanese
Agentic Tool Use (Enterprise)
Adversarial Robustness
Math
Spanish
Instruction Following
Agentic Tool Use (Chat)
Coding
2025 Scale AI. All rights reserved.
Agentic Tool Use (Chat)
Information
Data Samples
Select a model
Select a model
Select a question
Last updated: July 23, 2025
