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
Related Entities
Related Claims
UnverifiedIn the Pass@4 pass-rate test, o1 pro significantly outperformed o1.84% 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.73% similarUnverifiedIn the Codeforces rating, o1's score is far lower than that of o3-mini-high.73% 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% similarUnverifiedThe pass@1 metric was originally borrowed from the code generation evaluation domain (such as the HumanEval benchmark) to measure the probability of a model generating correct code on the first attempt.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)