Ethan Mollick 转评 Artificial Analysis v5 指数：开源权重模型与闭源差距扩大至 12 分

Ethan Mollick· @emollick · X·2026-10-28 10:59· 33 分钟前AI 评分57

AI 导读

Ethan Mollick 转发 Artificial Analysis v5 智能指数，该版本改用封闭基准（告别 GDPval-AA）后测得开源权重模型差距进一步拉大。领先的 Kimi K3.1 Pro（权重未发布）得 46 分，落后榜首 12 分，而 v4.3 时差距为 3 分；已发布权重中 DeepSeek V4.1 Flash 1017（max）和 GLM-5.3（max）最高 32 分。HLE-Diamond 与 Terminal-Bench-Science 差距最大，Kimi K3.1 Pro 分别为 37% 和 34%，Claude Opus 5.5（max）和 GPT-6 Astra（max）分别为 68% 和 63%。作者提醒对此结果需有所保留，但认为这与“尚未出现 Fable 级开源模型”的整体感受相符。

正文 · 原文

Artificial Analysis finally moves to closed benchmarks (goodbye GDPval-AA), and finds that open weights models are falling further behind than they had previously measured. Take with a grain of salt, but matches the general vibes that we haven't seen a Fable-class open model.

引用Artificial Analysis@ArtificialAnlys

Open weights models fall further behind in v5. The leader, Kimi K3.1 Pro (weights not yet released), scores 46, 12 points behind the leader, compared with a 3-point gap in v4.3. Of models with released weights, DeepSeek V4.1 Flash 1017 (max) and GLM-5.3 (max) score highest at 32, and Claude Haiku 5.5 (max) outscores all of them. The gap is widest on HLE-Diamond and Terminal-Bench-Science, where Kimi K3.1 Pro scores 37% and 34%, compared with 68% for Claude Opus 5.5 (max) and 63% for GPT-6 Astra (max).

在 X 查看被引用的帖子

来源：Ethan Mollick · x.com