Event ·Multi-source

Doximity Ask临床AI研究击败GPT-5.6和Claude Fable 5

Doximity Ask由Doximity开发，基于Fireworks平台训练。在Stanford Arise Lab的独立评估中，它超越GPT-5.6 Sol、Claude Fable 5、OpenEvidence等24个模型。该研究涉及12,747个专家评级，针对真实临床问题。结果表明专用临床模型在安全性上更优。

Current read

Doximity Ask在独立测试中把GPT-5.6和Claude Fable 5都干翻了，说明医学领域专用模型才是王道。

11 sources53° AI heatLast updated 2026/7/15 22:35:30

Evidence

11 sources

Primary sourceFireworks AI

2026/7/15 22:35:30View source

Related source 1Viking

2026/7/16 03:13:52View source

Related source 2IT之家

2026/7/14 01:44:58View source

Related source 3lmarena.ai

2026/7/15 16:37:10View source

Related source 4Decoder

2026/7/16 19:49:39View source

Related source 5Amjad Masad

2026/7/17 00:08:43View source

Related source 6orange.ai

2026/7/17 02:22:12View source

Related source 7AI Will

2026/7/17 05:30:37View source

Related source 8Jerry Liu

2026/7/17 15:35:55View source

Related source 9arXiv cs.AI

2026/7/17 17:46:23View source

Related source 10Thomas Wolf

2026/7/17 18:37:40View source

Conflict 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.

Open the story