Event ·Multi-source

SemiAnalysis 推出 GDPx 测试：最贵 AI 模型并非最强

SemiAnalysis 发布了名为 GDPx 的基准测试，将模型置于接近真实的工作环境中考察。测试场景涉及金融与法律任务，结果显示多数模型在这些领域几乎无法完成任务。测试还发现价格最高的模型并不等于表现最好的模型，成本与能力之间没有必然对应关系。

Current read

SemiAnalysis 搞了个 GDPx 测试，把模型扔进模拟的金融法律工作场景里跑，结果最贵的模型分数反而不是最高的。

7 sources47° AI heatLast updated 2026/11/3 12:08:00

Evidence

7 sources

Primary sourceGenk

2026/11/3 12:08:00View 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 3elvis

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

Related source 4kimmonismus

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

Related source 5rohanpaul_ai

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

Related source 6Latent 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