Unverified80% confidenceFactExact time
在Pass@1 Codeforces基准测试中，o1和o1 pro得分非常接近
1
Sources
80%
Confidence
Long-term
Relevance
2/5/2025
First Seen
Sources
o1、o1 pro与o3-mini-high编程能力深度对比：Deep Research实测分析
bilibilikate人不错2/5/2025
Related Entities
Related Claims
Unverified在Pass@4通过率测试中，o1 pro的表现显著优于o184% similarUnverified在AID基准测试中，o1 high（对应o1 pro）的编程能力得分超过60，优于o3-mini-high，但两者非常接近73% similarUnverified在Codeforces评分中，o1的得分远低于o3-mini-high73% similarUnverified在AIME 2024和CodeForces等权威基准测试中，DeepSeek R1的表现与OpenAI O1正式版不相上下67% similarUnverifiedpass@1指标最初从代码生成评测领域（如HumanEval基准）借鉴而来，用于衡量模型一次生成正确代码的概率64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/653API
curl https://kongchang.com/api/v1/knowledge/claims/653MCP
get_claim(id=653)