法律平台 Harvey 的 BigLaw Bench 测试结果同样亮眼，GPT-5.4 得分 91%，专业服务评测平台 Mercor 的 APEX-Agents 基准中也拿下了第一。
Pre-trainingOur 30B and 105B models were trained on large datasets, with 16T tokens for the 30B and 12T tokens for the 105B. The pre-training data spans code, general web data, specialized knowledge corpora, mathematics, and multilingual content. After multiple ablations, the final training mixture was balanced to emphasize reasoning, factual grounding, and software capabilities. We invested significantly in synthetic data generation pipelines across all categories. The multilingual corpus allocates a substantial portion of the training budget to the 10 most-spoken Indian languages.。关于这个话题，PDF资料提供了深入分析
这与阿里的逻辑异曲同工，不过，阿里的硬件嫁接在更庞大的商业根系上。。业内人士推荐新收录的资料作为进阶阅读
US president attends ‘dignified transfer’ of remains of soldiers killed in Kuwait drone strike wearing ‘USA’ golf cap，这一点在新收录的资料中也有详细论述
超过这个数，新的虚拟线程会排队等待。