{"version":"2026-10-19.observations.2","checkedAt":"2026-10-19","series":{"id":"epoch-eci","group":"capability","title":"综合能力指数：固定快照里的精选模型","question":"同一当前快照里的模型位于什么位置？","unit":"ECI指数点","denominator":"综合测试难度拟合；不是题目/工作成功比例","protocol":"Epoch当前固定CSV；不同测试和模型覆盖由拟合处理，不统一工具预算","scope":"2026-10-14的精选横截面；X为模型发布日，测量日未知","summary":"ECI把不同难度测试的表现拟合到一个相对能力尺度：分数较高，表示在这套测试与模型中处理较难题的表现更强；一个指数点没有对应一项工作或一小时。精选5个模型/档位的公布值介于150.00至167.33（ECI指数点）。日期较晚的点是较晚模型在此快照的成绩，不能读成该日已公开的能力历史；区间重叠不证明确定排序。","nextAction":"把指数用于寻找需要进一步核对的工具；仍须打开具体任务的测试协议和验收。","rows":[{"id":"obs-0363","label":"Claude Opus 5.5","value":167.33,"rawValue":"167.33","period":null,"modelDate":"2026-09-22","modelVersion":"","n":null,"ci":{"lower":164.06,"upper":171.68,"level":"90%来源区间"},"cost":null,"locator":"eci_scores.csv；Model=Claude Opus 5.5；snapshot=2026-10-14","notes":"综合指数；同名同日不同配置可能取各测试最佳；运行日未知，横轴是模型日","valueStatus":"reported","sourceId":"C-EPOCH","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null},{"id":"obs-0364","label":"GPT-6 Astra","value":166.45,"rawValue":"166.45","period":null,"modelDate":"2026-09-03","modelVersion":"","n":null,"ci":{"lower":163.34,"upper":171.46,"level":"90%来源区间"},"cost":null,"locator":"eci_scores.csv；Model=GPT-6 Astra；snapshot=2026-10-14","notes":"综合指数；同名同日不同配置可能取各测试最佳；运行日未知，横轴是模型日","valueStatus":"reported","sourceId":"C-EPOCH","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null},{"id":"obs-0365","label":"GPT-5.6 Sol","value":161.66,"rawValue":"161.66","period":null,"modelDate":"2026-07-09","modelVersion":"","n":null,"ci":{"lower":159.27,"upper":165.1,"level":"90%来源区间"},"cost":null,"locator":"eci_scores.csv；Model=GPT-5.6 Sol；snapshot=2026-10-14","notes":"综合指数；同名同日不同配置可能取各测试最佳；运行日未知，横轴是模型日","valueStatus":"reported","sourceId":"C-EPOCH","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null},{"id":"obs-0366","label":"GPT-5.5","value":159.1,"rawValue":"159.1","period":null,"modelDate":"2026-04-23","modelVersion":"","n":null,"ci":{"lower":156.66,"upper":162.27,"level":"90%来源区间"},"cost":null,"locator":"eci_scores.csv；Model=GPT-5.5；snapshot=2026-10-14","notes":"综合指数；同名同日不同配置可能取各测试最佳；运行日未知，横轴是模型日","valueStatus":"reported","sourceId":"C-EPOCH","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null},{"id":"obs-0367","label":"GPT-5","value":150,"rawValue":"150.0","period":null,"modelDate":"2025-08-07","modelVersion":"","n":null,"ci":null,"cost":null,"locator":"eci_scores.csv；Model=GPT-5；snapshot=2026-10-14","notes":"综合指数；同名同日不同配置可能取各测试最佳；运行日未知，横轴是模型日","valueStatus":"reported","sourceId":"C-EPOCH","actualCoverage":null,"runAt":null,"scorePublishedAt":null,"toolBudget":null}],"sourceIds":["C-EPOCH"],"xKind":"model_date","connect":false,"readingIds":["reading-measures"],"taskId":null,"boundaryTasks":["C03","M01"],"actualCoverage":null,"evidenceStatus":"active"},"sources":[{"id":"C-EPOCH","title":"Epoch ECI固定快照","url":"https://epoch.ai/data/eci-documentation","version":"2026-10-14取得的CSV；ECI与FrontierCode独立指标","locator":"eci_scores.csv；processed_data_for_eci.csv指定benchmark行","scope":"跨测试拟合的综合指数；组件保留模型版本，可能取同名同日不同配置的最高成绩","license":"Epoch数据CC BY 4.0（当前官方链接核对），署名Epoch AI","limit":"模型日不等于测量日；本次快照不是逐日历史；组件0–1分不称工作通过率","publishedAt":null,"readAt":"2026-10-15","collectedAt":"2026-10-14","status":"active","nextReview":"2027-01-13","methods":["https://epoch.ai/data/eci-documentation/methodology"],"family":"C-EPOCH"}],"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}