Unverified85% confidenceFactTime unknown
O4-mini在AIME数学竞赛评测中接入Python工具后得分高达99.5%
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026
Sources
OpenAI三箭齐发:O3、O4-mini与Codex CLI深度解析
bilibili鱼C-小甲鱼
Related Entities
Related Claims
Unverified在SWE-Bench评分中,o1的得分远高于o3-mini medium,但略低于o3-mini-high65% similarUnverifiedSonnet 4.6与Opus 4.6相比,在大多数基准测试中表现几乎持平,但推理速度更快、调用成本更低63% similarUnverified在Codeforces评分中,o1的得分远低于o3-mini-high62% similarUnverifiedO4-mini在Codeforces编程竞赛中排名进入全球前20061% similarUnverifiedPython的浮点数遵循IEEE 754双精度浮点数标准,使用64位二进制来表示一个小数60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/22477API
curl https://kongchang.com/api/v1/knowledge/claims/22477MCP
get_claim(id=22477)