Skip to main navigation
Skip to search
Skip to main content
Ben-Gurion University Research Portal Home
Help & FAQ
Link opens in a new tab
Search content at Ben-Gurion University Research Portal
Home
Profiles
Research output
Research units
Prizes
Press/Media
Student theses
Projects
Activities
Datasets
Research Labs
A benchmark of expert-level academic questions to assess AI capabilities
Center for AI Safety
, Scale AI
, HLE Contributors Consortium
Department of Mechanical Engineering
Research output
:
Contribution to journal
›
Article
›
peer-review
18
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'A benchmark of expert-level academic questions to assess AI capabilities'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Model Capabilities
100%
AI Capabilities
100%
Academic Questions
100%
Large Language Models
75%
Closed End
50%
Popular
25%
Rapid Advancement
25%
World Wide Web
25%
Natural Sciences
25%
Multi-task
25%
Policy Making
25%
Level Closed
25%
Subject Matter Experts
25%
Broad Subject
25%
Human Knowledge
25%
Multiple-choice Questions
25%
Low Accuracy
25%
Short-answer Questions
25%
Academic Benchmark
25%
Multimodal Benchmark
25%
Automated Grading
25%
Computer Science
Large Language Model
100%
Artificial Intelligence
100%
Answer Question
20%
Subject Matter Expert
20%
Information Retrieval
20%
Subject Coverage
20%
Social Sciences
Large Language Model
100%
Artificial Intelligence
100%
Mathematics
20%
Multiple Choice Test
20%
Natural Science
20%