Unverified85% confidenceFactTime unknown
o1系列模型在国际数学奥林匹克预选题上的表现达到了金牌水平
1
Sources
85%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
awesome-LLM-resources：GitHub 8K Star最全大语言模型学习资源库解析
githubWangRongsheng
Related Entities
Related Claims
UnverifiedAlphaGeometry solved 25 out of 30 problems in a test on historical International Mathematical Olympiad geometry problems, approaching the level of gold medalists58% similarUnverifiedIn the AID benchmark, o1 high (corresponding to o1 pro) scored above 60 in programming ability, outperforming o3-mini-high, though the two are very close.53% similarUnverifiedThe final overall test scores of the two models ended in a tie52% similarUnverifiedIn programming benchmarks, Codex-1 outperformed Claude 3.7 and O3 High.52% similarUnverifiedIn the Pass@4 pass-rate test, o1 pro significantly outperformed o1.50% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/32608API
curl https://kongchang.com/api/v1/knowledge/claims/32608MCP
get_claim(id=32608)