Verified65% confidenceBenchmarkExact time
GPT-4 has reached or surpassed the human average on the bar exam and medical licensing examinations.
3
Sources
65%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
The Revenge of the Philosophy Majors in the AI Era: Why Critical Thinking Has Become the New Scarce Resource
hackernewshackernews7/7/2026
Related Claims
VerifiedGPT-4 ranked in the top 10% on the US bar exam.77% similarUnverifiedLarge models such as GPT-4 have reached or exceeded entry-level human performance in fields including legal assistance, junior programming, translation, customer service, and content creation.77% similarUnverifiedGPT-4在美国执照医师考试USMLE中通过率超过90%71% similarVerifiedGPT-4 and Claude 3 achieve pass@1 rates exceeding 85% on the HumanEval code benchmark.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/292652API
curl https://kongchang.com/api/v1/knowledge/claims/292652MCP
get_claim(id=292652)