Unverified50% confidenceFactExact time
在SWE-Bench评分中，o1的得分远高于o3-mini medium，但略低于o3-mini-high
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Related Claims
Unverified在Codeforces评分中，o1的得分远低于o3-mini-high80% 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74% similarUnverified在SWE-Bench Multilingual测试中，HY3得分75.8，略微落后于DeepSeek V4 Pro的76.269% similarUnverified在Chatbot Arena（由LMSYS组织运营）排行榜上，O3 Mini的得分略高于DeepSeek R169% similarUnverifiedCodex One在SWE-bench上的表现略优于O3 High，在OpenAI内部软件工程任务上准确率达到75%，而O3 High为70%68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/59200API
curl https://kongchang.com/api/v1/knowledge/claims/59200MCP
get_claim(id=59200)