Primary sourceDeepLearning.AI
View sourceEvent ·Multi-source
Gemini 4 Argon 幻觉率 15%,远低于 GPT-6 Astra 的 51%
Gemini 4 Argon 在 AA-Omniscience 基准上的幻觉率为 15%,同榜的 GPT-6 Astra 为 51%。该模型还在 Vals Index 上排名第一,在法律等知识工作场景表现突出。目前它仅向 Google Fairwind 计划中的网络安全防御者开放使用。
Current read
Google 的 Gemini 4 Argon 把幻觉率压到 15%,是 GPT-6 Astra 51% 的近三分之一,不过暂时只有 Fairwind 项目的安全人员能用。
11 sources68° AI heatLast updated 2026/10/13 16:00:00
Evidence
11 sourcesRelated source 1Artificial Analysis
View sourceRelated source 2Epoch AI
View sourceRelated source 3TestingCatalog
View sourceRelated source 4Blognone
View sourceRelated source 5Bindu Reddy
View sourceRelated source 6kimmonismus
View sourceRelated source 7Ethan Mollick
View sourceRelated source 8量子位
View sourceRelated source 9rohanpaul_ai
View sourceRelated source 10IT之家
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.