gemini-4POST
Gemini 4 Argon 早期访问：250+ 评测中 99% 数据吻合
团队提前拿到 Gemini 4 Argon，跑了 250 多个评测并逐格对照申报文件数字，99% 以上吻合，25 项最难任务中 22 项达前沿水平。
Vinoo Ganesh
@VinooGanesh20 天前收录原推发布于 2026.10.14
Vinoo Ganesh @VinooGanesh原推发布于 2026.10.14
We had early access to Gemini 4 Argon from @GoogleDeepMind and ran it through 250+ evals, each scored cell by cell against figures cited to the filing that reported them. 99%+ of figures matched. Frontier on 22 of our 25 hardest tasks. Shoutout to @gl3nnleblanc for leading the work!
这条是引用着另一条写的：x.com/gl3nnleblanc/status/2110043072801169611
x.com/vinooganesh/status/2110056736560398571采集于 2026.10.14 10:17