Home Model series Claude Opus Claude Opus 4.7 Claude Opus 4.7 · OfficeQA · Pro 133-question subset · Scores and configurations Claude Opus 4.7 · OfficeQA · Pro 133-question subset · Scores and configurations Claude Opus 4.7 record for OfficeQA · Pro 133-question subset. 2 score records for this release, including 2 exact values (may include historical records). Includes 2 source locations.
Scores and evaluation conditions Claude Opus 4.7 · OfficeQA scores and configurations Metric and score Configuration and evaluation conditions Sources Exact-match accuracy 80.6% Reported 80.6% · Unit % Published Unconfirmed
OfficeQA / OfficeQA Pro,exact match Settings System Card §8.1 standard configuration; exact-match grading; 0% allowable relative error. Unknowns none recorded Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol OfficeQA Pro; exact-match grading. Conditions 0% allowable relative error; §8.1 standard configuration unless noted. View this score in rankings Exact-match accuracy 65% Reported 65.0% · Unit % Published Unconfirmed
OfficeQA Pro current announcement update Settings Claude Opus 4.7; announcement figure reported setting; per-result effort and evaluator not specified. Unknowns 题集、harness、effort和trials未在该图注明,不能与系统卡的其他运行设置强并。 Tools Tool access not recorded Reasoning budget not recorded Framework not recorded Protocol OfficeQA Pro; Correctness (%); announcement figure updated May 4, 2026. Conditions 只取图上明确数字标签。配置、任务集与评测设置未披露,独立于系统卡其他运行;不因数值相同合并不同测试。 页面注明May 4更新该图,但保存HTML另有September 30修改时间;没有该图May 4历史字节,当前65.0%的精确首次公布日不确定。 View this score in rankings
Benchmark versions and metrics Aliases OfficeQA Pro
Exact-match accuracy · % · Higher is better