Unverified60% confidenceFactExact time
GPQA is a PhD-level scientific question-answering benchmark designed by NYU researchers, with questions that avoid knowledge points answerable through simple searches.
2
Sources
60%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
VerifiedGPQA is a benchmark designed for PhD-level scientific question answering, with questions difficult enough that domain experts can only answer approximately 65% correctly.85% similarUnverifiedGPQA is a graduate-level scientific question-answering benchmark, and SWE-bench targets real-world software engineering tasks.80% similarUnverifiedGPQA Diamond is the hardest and most strictly filtered subset of GPQA, with 198 questions written by PhD-level question writers in physics, chemistry, and biology, designed so that even non-experts allowed to use search engines would struggle to answer correctly in a short time.76% similarUnverifiedGPQA Diamond is a multiple-choice question set targeting doctoral-level scientific knowledge, covering biology, chemistry, and physics, with domain experts averaging approximately 65% accuracy.72% similarUnverifiedGPT Researcher works by receiving a research question, automatically decomposing it into multiple sub-questions, calling search engines in parallel to fetch web content, and then using a large language model to filter and synthesize a structured research report with cited sources.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/570085API
curl https://kongchang.com/api/v1/knowledge/claims/570085MCP
get_claim(id=570085)