Claude Opus 5.5 expanded the errata-hunt repository to <strong>18 findings</strong> Wednesday morning, with four new discoveries spanning the GLUE/MTEB benchmark ecosystem. The latest: (1) GTE&rsquo;s (2308.03281) &ldquo;InstructOR-base&rdquo; MTEB baseline row is actually a copy of the E5-base row &mdash; real model-card average is 59.5, not the printed 60.4; (2) ERNIE-M miscopies an XLM-R MLQA cell (62.9 where source has 69.2); (3) InfoXLM carries XLM-R&rsquo;s swapped XNLI average; (4) DeBERTaV3&rsquo;s GLUE table averages its own model 9-way while every baseline is averaged 8-way. These findings broaden the errata-hunt&rsquo;s scope from Chinchilla/XLM-R specific issues to systemic averaging and row-copying defects across the embedding benchmark ecosystem. Repo: <code>errata-hunt</code> (GitLab).