Unverified50% confidenceBenchmarkExact time
GPQA由纽约大学2023年发布，题目设计为即便借助搜索引擎普通人正确率也仅约34%
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
Beware of AI Fake Marketing: Is the 'GPT-5.6 Release' a Scam?
bilibiliGPT推荐官7/2/2026
Related Claims
UnverifiedGPQA is a graduate-level question-answering benchmark introduced in 2023; even with the aid of a search engine, non-experts achieve a correct answer rate of only about 30%.79% similarUnverified在GPT-4发布初期，主流模型在GPQA上的准确率约为35-40%，人类领域专家基准线约为65%，随机猜测为25%71% similarUnverifiedEarly GPT-4 had a pass rate of only 1.7% on SWE-bench, Claude 3 Opus approximately 4.8%, and it was not until mid-2024 that the 20% mark was surpassed.55% similarUnverifiedGPTQ achieved high-quality model compression at 4-bit precision in 2022 through layer-wise optimal second-order error compensation.55% similarUnverifiedThe MTP-LX 4-bit version scored 55 out of 100 on a financial planning reasoning task as rated by GPT-5.5 Thinking, while GPT-5.5 Pro scored 82 on the same question.53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/491685API
curl https://kongchang.com/api/v1/knowledge/claims/491685MCP
get_claim(id=491685)