Unverified70% confidenceBenchmarkExact time
In 2023, large language models such as GPT-4 reached or exceeded the passing threshold on all stages of the USMLE.
2
Sources
70%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
以人为本的AI：医疗与设计领域的真实落地实践
Related Claims
Unverified2023年后以GPT-4为代表的大语言模型具备了零样本工具调用能力81% similarUnverifiedAfter 2023, the emergence of large language models such as GPT-4 made free conversational speaking practice possible.80% similarUnverifiedGPT-3 first demonstrated the emergent capabilities of ultra-large-scale language models in 2020, but its interaction paradigm was limited to single-turn text generation.78% similarUnverified以GPT-4为代表的大语言模型在2022年前后在自然语言理解、逻辑推理和代码生成上实现了质的飞跃，为智能体提供了通用大脑77% similarVerifiedGPT-4o, released in 2024, directly integrated image generation capabilities into a multimodal large language model.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/597901API
curl https://kongchang.com/api/v1/knowledge/claims/597901MCP
get_claim(id=597901)