跳到正文
Simon Willison 博客·· 2 小时前同事件AI 评分81

Simon Willison 实测 OpenAI 新模型 GPT-6.2 Astra 与 GPT-6.2 Sol

GPT‑6.2 Astra and GPT‑6.2 Sol

AI 导读

OpenAI 发布 GPT-6.2 Astra(面向高难度项目的旗舰模型)和 GPT-6.2 Sol(面向日常工作的通用模型),API 名称分别为 gpt-6.2-astra 和 gpt-6.2-sol。

同一件事,精选收录的是《OpenAI 发布 GPT-6.2 Astra 与 GPT-6.2 Sol》

正文 · AI 翻译

GPT‑6.2 Astra 与 GPT‑6.2 Sol

OpenAI:

我们推出 GPT‑6.2 Astra,这是面向最艰巨项目的新一代前沿模型;同时推出 GPT‑6.2 Sol,一款高效、多用途的模型,适合日常工作。

这两款模型已在 API 中上线,型号为 gpt-6.2-astra 和 gpt-6.2-sol。我发布了 LLM 0.38,已支持这两款新模型。

6.2 Astra 的价格是 6 Astra 的 80%——输入 $8/百万 token,输出 $40/百万 token,与 Claude Fable 5.2 同价(后者也是前代的 80%)。6 Astra 和 Fable 5 都是 $10/$50。缓存价格折扣更大——每百万 token $0.40,而旧模型是 $1。这对长时间运行的智能体会话来说是个好消息。

GPT-6.2 Sol 的价格与 6.1 Sol、6 Sol 相同,都是 $2/$10——是 GPT-5.6 Sol($4/$20)的一半。

这里是 GPT-6.2 Sol 的鹈鹕和 GPT-6.2 Astra 的鹈鹕。6.2 Astra 的 max 档鹈鹕长这样:

Good bicycle, good pelican, one wing is on the handlebars with fingers, the other wing is behind. Feet on the correct side of the frame. Nice gradiants. Good pouch, hooked bill.

我有一份完整的对比表格,下面是 high/xhigh/max 三档鹈鹕与之前 Sol、Astra 版本的对比:

Twelve pastel illustrations compare four models drawing a pelican riding a bicycle at three effort levels. All twelve have a recognizable pelican and bicycle. The clearest differences are in the feather detail and how convincingly the bird steers and pedals. gpt-6.2-astra has the most detailed Max drawing (88.71¢), with layered feathers, a trailing red scarf, and a wing on the handlebars. Xhigh (17.70¢) adds a green cap and keeps the seaside setting. High (11.55¢) simplifies the feathers while keeping the riding pose clear. gpt-6.2-sol shows a convincing pedaling pose at both Max (13.69¢) and Xhigh (6.74¢), with one foot higher than the other and a wing reaching forward. At High (2.41¢), the bird sits lower and the handlebars are harder to distinguish. gpt-6-astra gives the bird a long wing that follows the curve of the handlebars at Max (63.21¢). Xhigh (33.85¢) shows two bent legs on the pedals. At High (18.37¢), one leg stretches almost straight down, making the pose look stiffer. gpt-6.1-sol uses nearly the same long-necked bird with a wing on the bars at Max (13.48¢) and Xhigh (5.39¢). At High (3.66¢), the bird folds its wing against its body and appears to ride hands-free.

我还用最近一次的基准测试提示词跑了这两款模型,在 Codex CLI 中使用“Ultra”努力档位:

Make a three js animation where yonkers stands up as a big mech (cool stand up motion) and stomps around manhattan and queens and Brooklyn, use openstreetmap mapping data

这是 Sol,这是 Astra。两者都没能把 Yonkers 变形为大机甲,至少与 Claude Fable 5.2 和 Gemini 4 Carbon 相比是这样。

这段视频展示了 Astra 和 Sol 的动画同时播放:

我在 Codex 桌面应用里用 GPT-6.2 Astra(Ultra)生成了这段视频,提示词是:

https://static.simonwillison.net/static/2026/yonkers-gpt-6.2-astra-ultra/index.html and https://static.simonwillison.net/static/2026/yonkers-gpt-6.2-sol-ultra/index.html  are two videos of the same thing by two different models

I need a video of the first 10 seconds where the top half of the video plays the first and the bottom half plays the second

I need an overlaid label of "GPT-6.2 Astra" on the top half and "GPT-6.2 Sol" on the bottom half. These labels should be tastefully positioned.

Make the video square and 2000x2000 pixels

然后稍后:

OK make it 20s

这里是导出的对话记录。

目前围绕这两款新模型的讨论褒贬不一。Astra 6.2 在多项基准测试上的得分不如 Fable 5.2,我也看到一些人抱怨它的沟通风格让人困惑。Theo Browne 的评测(以他在预发布期间发给 OpenAI 的反馈信形式)里有个很有用的例子:

当这个模型处理长任务时,它能调用大量子智能体并管理得相当不错。然后它会突然问你一些莫名其妙的内部实现细节,这些东西你根本不可能理解,更别说给出意见了。

我发了“/goal 给《星际拓荒》做一个新关卡”。两小时后,它“卡住”了,因为它想问我“r24 的审查器是把它的片段写到 24_g521.mp4 还是 24_p11.mp4?”

标签:ai、openai、generative-ai、llms、llm-pricing、pelican-riding-a-bicycle、llm-release、theo-browne、gpt、yonkers-rising

来源:Simon Willison 博客 · simonwillison.net

事件后续 · 2

查看事件全部