Unverified50% confidenceFactExact time
人类领域专家在 GPQA 上平均约得 65%
1
Sources
50%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
OpenAI GPT-Live Voice Model: How Full-Duplex Interaction Reshapes Human-AI Conversation
bilibili皮皮蟹勇闯天涯7/10/2026
Related Claims
Unverified在 GPQA 上，领域博士生平均正确率约65%，非专家用户约34%82% similarUnverifiedGPQA was designed by a research team at New York University; non-experts using search engines achieve an accuracy of approximately 34%, while domain experts average approximately 65%.73% similarUnverifiedGPQA Diamond由纽约大学研究团队构建，人类专家（博士生）的平均正确率约为65%，非专业人类约为34%72% similarUnverifiedHuman experts score an average of approximately 55%–65% on the MMMU Pro benchmark.65% similarUnverifiedGPQA 是由纽约大学研究者 David Rein 等人于2023年设计的博士级科学问答基准，含448道题目，领域博士生平均正确率约65%，非专家约34%65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/500219API
curl https://kongchang.com/api/v1/knowledge/claims/500219MCP
get_claim(id=500219)