Unverified85% confidenceFactTime unknown
o1模型在国际数学奥林匹克预选题上的表现接近金牌水平，在Codeforces编程竞赛中达到了89百分位
1
Sources
85%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
GitHub 8000+ Star：最全LLM学习资源库深度解析
githubWangRongsheng
Related Entities
Related Claims
Unverifiedo1在国际数学奥林匹克级别问题上正确率超过80%，远高于GPT-4的约13%70% similarUnverifiedIn the Elo system, a rating difference of 400 points means the stronger player's expected win rate is approximately 91%, with player A's winning probability being 1/(1+10^((Rb-Ra)/400)).58% similarUnverifiedOn the Terminal Bench 2.1 benchmark, Ultra mode approaches 92%, surpassing competitors' performance of 88%.57% similarUnverifiedThe solve rate of current top AI models on SWE-bench remains far below the level implied by their competition performance.56% similarUnverifiedIn the experimental design, the AI used an 8:2 split to reserve 20% as an independent test set, and applied 5-fold cross-validation on the 80% training set to avoid data leakage.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/34543API
curl https://kongchang.com/api/v1/knowledge/claims/34543MCP
get_claim(id=34543)