Artificial Analysis：幻觉门控后多数模型排名大幅下滑，Grok 4.7 登顶
Hallucination gating changes the picture for most models. Muse Spark 1.3 (max) from @AIatMeta ranks first before the hallucination gate at 26.7%, but falls to 8
Artificial Analysis 指出，加入幻觉门控后多数模型表现大幅下滑。Meta 的 Muse Spark 1.3 (max) 门控前以 26.7% 排名第一，计入幻觉后降至 8.9%，使 xAI 的 Grok 4.7 (xhigh) 以 9.4% 升至榜首。GLM-5.3 (max) 有 13.9% 任务通过全部标准，但无重大幻觉的仅 0.3%；Kimi K3 (max) 从 16.7% 降至 5.3%，Claude Sonnet 5.5 (max with fallback) 从 11.7% 降至 2.8%，GPT-6.1 Sol (max) 降幅较小，从 7.5% 到 6.9%。
推荐理由
AI 评分 58
幻觉门控让多数模型排名大幅下滑，读者可据此重新理解各家模型在真实任务中的可用性差异。
主题
正文
当前显示原文，中文全文译文尚未就绪。
Hallucination gating changes the picture for most models. Muse Spark 1.3 (max) from @AIatMeta ranks first before the hallucination gate at 26.7%, but falls to 8.9% after accounting for hallucinations, leaving Grok 4.7 (xhigh) from @SpaceXAI first at 9.4% on the headline metric. GLM-5.3 (max) passes all criteria for 13.9% of tasks but just 0.3% without a material hallucination, Kimi K3 (max) from @Kimi_Moonshot falls from 16.7% to 5.3%, and Claude Sonnet 5.5 (max with fallback) from 11.7% to 2.8%. GPT-6.1 Sol (max) falls relatively little, from 7.5% to 6.9%.