www.anthropic.com
网页
综合
Search Anthropic
… we have been testing this model, and what we have found over the past month. Eval awareness in Claude Opus 4.6’s BrowseComp performance Evaluating Opus 4.6 on BrowseComp, we found cases whe…
2026-11-13
自动蜘蛛
相关度 2.8