Event ·Multi-source

DeepSeek 新模型在 GDPval 基准上超越 OpenAI

GDPval 是 OpenAI 发布的一项经济价值任务基准。推文称 OpenAI 模型在该基准上表现不佳，而 DeepSeek 新模型在其上位居中国模型、开源模型和速度三类榜单之首，呈帕累托占优。该推文来自 X 用户 teortaxesTex。

Current read

DeepSeek 新模型在 OpenAI 自家的 GDPval 基准上把开源和中国模型都拿了第一，还比同分模型快，数据点很硬。

11 sources63° AI heatLast updated 2026/10/19 06:02:50

Evidence

11 sources

Primary sourceTeortaxes

2026/10/19 06:02:50View source

Related source 1TestingCatalog

2026/10/17 10:49:40View source

Related source 2Artificial Analysis

2026/10/19 16:25:46View source

Related source 3Decoder

2026/10/20 18:56:15View source

Related source 4歸藏(guizang.ai)

2026/10/17 08:56:20View source

Related source 5Gorden Sun

2026/10/17 12:55:33View source

Related source 6@koltregaskes

2026/10/18 23:30:01View source

Related source 7Liputan6 Tekno

2026/10/21 04:11:49View source

Related source 8The Information

2026/10/17 13:30:04View source

Related source 9Nathan Lambert

2026/10/17 14:15:29View source

Related source 10Andrew Curran

2026/10/18 03:13:32View 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