{"version":"2026-10-19.observations.2","checkedAt":"2026-10-19","series":{"id":"aime-cost","group":"cost","title":"AIME2025：同赛事公布费用/题","question":"一次题目评测的费用，与完整工作成本差在哪里？","unit":"美元/题","denominator":"同一赛事模型详情页公布的成本/题；不含人的审查、失败接管和维护","protocol":"与答案行同模型/档位/官方页配对；费用不是质量相同的工作流程净成本","scope":"只选有限事实摘要，未知费用不补值；横截面按模型/档位编号，日期另见卡片","summary":"低费用不等于更适合你的工作。成本还包括失败尝试、核验、返工、接管及必要资料工具。 精选包括同系列high/xhigh以核对档位差异，按模型编号展示；不是完整61项或最优模型推荐。","nextAction":"把费用当预算背景；另记完整人的活动人时、机器运行与等待、同质量基线。","rows":[{"id":"obs-0387","label":"GPT-5.2 (xhigh)","value":0.18,"rawValue":0.18,"period":null,"modelDate":"2025-12-11","modelVersion":"openai_gpt_52","n":null,"ci":null,"cost":0.18,"locator":"https://matharena.ai/models/openai_gpt_52；AIME2025 row","notes":"同赛事页的费用/题；不同模型的token、推理档位可能不同；没有取得完整工作流成本","valueStatus":"reported","sourceId":"C-AIME","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null},{"id":"obs-0393","label":"GPT-5.2 (high)","value":0.11,"rawValue":0.11,"period":null,"modelDate":"2025-12-11","modelVersion":"openai_gpt_52_high","n":null,"ci":null,"cost":0.11,"locator":"https://matharena.ai/models/openai_gpt_52_high；AIME2025 row","notes":"同赛事页的费用/题；不同模型的token、推理档位可能不同；没有取得完整工作流成本","valueStatus":"reported","sourceId":"C-AIME","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null},{"id":"obs-0388","label":"GPT-5 (high)","value":0.14,"rawValue":0.14,"period":null,"modelDate":"2025-08-07","modelVersion":"openai_gpt_5","n":null,"ci":null,"cost":0.14,"locator":"https://matharena.ai/models/openai_gpt_5；AIME2025 row","notes":"同赛事页的费用/题；不同模型的token、推理档位可能不同；没有取得完整工作流成本","valueStatus":"reported","sourceId":"C-AIME","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null},{"id":"obs-0389","label":"o4-mini (high)","value":0.062,"rawValue":0.062,"period":null,"modelDate":"2025-04-16","modelVersion":"openai_o4_mini_high","n":null,"ci":null,"cost":0.062,"locator":"https://matharena.ai/models/openai_o4_mini_high；AIME2025 row","notes":"同赛事页的费用/题；不同模型的token、推理档位可能不同；没有取得完整工作流成本","valueStatus":"reported","sourceId":"C-AIME","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null},{"id":"obs-0390","label":"DeepSeek-R1","value":0.025,"rawValue":0.025,"period":null,"modelDate":"2025-01-21","modelVersion":"deepseek_deepseek_r1","n":null,"ci":null,"cost":0.025,"locator":"https://matharena.ai/models/deepseek_deepseek_r1；AIME2025 row","notes":"同赛事页的费用/题；不同模型的token、推理档位可能不同；没有取得完整工作流成本","valueStatus":"reported","sourceId":"C-AIME","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null},{"id":"obs-0391","label":"gpt-4o","value":0.009,"rawValue":0.009,"period":null,"modelDate":"2024-08-06","modelVersion":"openai_gpt_4o","n":null,"ci":null,"cost":0.009,"locator":"https://matharena.ai/models/openai_gpt_4o；AIME2025 row","notes":"同赛事页的费用/题；不同模型的token、推理档位可能不同；没有取得完整工作流成本","valueStatus":"reported","sourceId":"C-AIME","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null}],"sourceIds":["C-AIME"],"xKind":"label","connect":false,"readingIds":["reading-cost"],"taskId":null,"boundaryTasks":["F01","M01"],"actualCoverage":null,"evidenceStatus":"active"},"sources":[{"id":"C-AIME","title":"MathArena AIME2025固定赛事","url":"https://matharena.ai/","version":"2026-10-14官方模型详情页AIME2025行的有限摘要","locator":"逐模型详情页AIME2025 Accuracy/CI/Cost/Output Tokens","scope":"公开2025题组；模型/推理档位逐行保留","license":"网页数据许可未单独确认；仅少量公布事实摘要与原文链接，不镜像题目/产物","limit":"单行实际运行日与重复次数未知；赛事后模型可能见过公开题；不是研究级证明","publishedAt":null,"readAt":"2026-10-15","collectedAt":"2026-10-14","status":"active","nextReview":"2027-01-13","methods":["https://github.com/eth-sri/matharena"],"family":"C-AIME"}],"temporalRule":"观察期可画同来源趋势；模型发布日只展开当前横截面，未知运行/首次公开日不补。使用份额/企业采用/测试分不互换，不据此生成职业AI化比例。","actualCoverage":null}