Event ·Multi-source

SemiAnalysis 发布 GDPx 基准：最强模型仅得 12%

SemiAnalysis 发布 GDPx 基准，用于衡量模型在高价值领域的智能体能力。该基准达到前沿难度，目前最好的模型只拿到 12%（7 题中答对 1 题）。Elvis Saravia 转评提到，Gemini 新版本 Carbon 在协调与持久性任务上表现明显提升。这类脱离标准基准的测试正在揭示各模型能力上的差异。

Current read

SemiAnalysis 搞了个新基准 GDPx，最强模型只拿 12%，里面 Gemini Carbon 在智能体任务上表现挺亮眼，可以看看。

6 sources67° AI heatLast updated 2026/11/2 15:48:43

Evidence

6 sources

Primary sourceelvis

2026/11/2 15:48:43View source

Related source 1Varun Mohan

2026/11/2 03:02:17View source

Related source 2Sundar Pichai

2026/11/2 04:34:36View source

Related source 3kimmonismus

2026/11/2 09:03:30View source

Related source 4rohanpaul_ai

2026/11/2 12:45:11View source

Related source 5Latent Space (swyx)

2026/11/3 05:35:00View 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