agentPOST
Opus 5.5 对齐测试取得史上最高分
该模型发布前经 METR、Frontier Design 等外部评估，在最全面对齐测试中拿到迄今最强成绩。
Claude
@claudeai2026.09.23收录原推发布于 2026.09.23
Claude @claudeai原推发布于 2026.09.23
Opus 5.5 is our first model since we called for pacing the frontier. As with previous models, it was tested by external evaluators before release, including METR and Frontier Design. On our most comprehensive alignment test, it achieves the strongest score to date.
x.com/claudeai/status/2102435514855158124采集于 2026.09.23 10:43