Ethan Mollick 评 Gemini 4 Argon 攻克 ARC-AGI：知名难题基准时代落幕

Ethan Mollick· @emollick · X·2026-10-16 07:29· 2 小时前AI 评分70

AI 导读

Ethan Mollick 引用 @arcprize 数据称，Gemini 4 Argon 在 ARC-AGI (Verified) 上 ARC-AGI-3 得分 97.5%（provider adapter harness，花费 $4.8K），标准 harness 下为 49.8%；ARC-AGI-2 得分 91.3%，ARC-AGI-1 得分 98.5%，Google DeepMind 是第二个在 ARC-AGI-3 上超过 95% 的前沿实验室。作者认为智能体框架加上更强模型意味着 METR Long Tasks、GDPval、ARC-AGI-3 这些著名难题基准相继失去区分度。

正文

Harnesses + smart models = the end of the last famous hard benchmarks.

Models can now work for extremely long times (bye, METR Long Tasks), they can output professional documents with correct math (so long, GDPval) and they can solve complex novel puzzles (farewell, ARC-AGI-3).

引用ARC Prize@arcprize

Gemini 4 Argon from @Google on ARC-AGI (Verified): - ARC-AGI-3: 97.5%, $4.8K (provider adapter harness), 49.8%, $5.8K (standard harness) - ARC-AGI-2: 91.3%, $0.32/task - ARC-AGI-1: 98.5%, $0.16/task Google DeepMind is the second frontier AI lab to score above 95% on ARC-AGI-3.

在 X 查看被引用的帖子

来源：Ethan Mollick · x.com