---
title: "GPT-5.6系列发布：Luna、Terra、Sol三款模型亮相"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Jul/9/gpt-5-6/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_3d8f58ac8bbfa71493936d81"
published: "2026-07-09T19:46:38.000Z"
score: 79
channel: "tech"
tags: ["Agent","API","Claude Fable 5","GPT-5.6","OpenAI","大语言模型"]
---

# GPT-5.6系列发布：Luna、Terra、Sol三款模型亮相

## AI 点评

> GPT-5.6在代理任务上的突破令人振奋，但SWE-Bench的争议提醒我们标榜成绩需谨慎。对需要复杂推理和长程自主任务的开发者来说，Sol可能成为新选择；而对成本敏感的场景，Luna和Terra性价比突出。API新特性如编程工具调用和多Agent子代理值得深入探索。

## 速览

OpenAI今日正式发布GPT-5.6系列旗舰模型，包括Luna、Terra、Sol三款尺寸。基准测试显示，Sol在“Agent最后考试”中以53.6分超越Claude Fable 5（40.5分），提升13.1分。即使在中等推理模式下，Sol也能以约四分之一成本领先Fable 5 11.4分。Terra和Luna则以约十六分之一成本超越Fable 5。新模型引入编程工具调用、多Agent子代理、提示缓存断点等API特性。但SWE-Bench Pro基准测试中Fable 5仍领先（80% vs Sol的64.6%），OpenAI此前发文质疑该基准约30%任务存在问题。

## 关键点

- GPT-5.6系列包括Luna、Terra、Sol三款模型，定价从$1/$6到$5/$30每百万token。
- 在Agent长期工作流基准“Agents’ Last Exam”上，Sol以53.6分大幅领先Claude Fable 5（40.5分）。
- 新API支持：编程工具调用（JavaScript编排）、多Agent子代理、提示缓存断点、图像原始分辨率。
- SWE-Bench Pro上Fable 5仍领先，OpenAI此前指该基准约30%任务存在缺陷。

## 全文

OpenAI's latest flagship model hit general availability this morning, and comes in three sizes: Luna, Terra, and Sol (from smallest to largest). The new models are priced per 1M input/output tokens as Luna $1/$6, Terra $2.50/$15, Sol $5/$30. For comparison, the Claude Opus series are $5/$25 and the Claude Fable 5 is $10/$50, but price-per-million tokens doesn't tell us much now that the number of reasoning tokens can differ so much between models for the same task. OpenAI's biggest benchmark claim concerns long-running agentic performance, with one benchmark showing all three models outperforming Claude Fable 5: We trained GPT-5.6 to get more useful work from every token. On Agents’ Last Exam, an evaluation of long-running professional workflows across 55 fields, GPT-5.6 Sol sets a new high of 53.6, eclipsing Claude Fable 5 (adaptive reasoning) by 13.1 points. Even at medium reasoning, it beats Fable 5 by 11.4 points at roughly one-quarter the estimated cost. That efficiency extends to smaller models, which are essential to making intelligence more abundant and affordable: GPT-5.6 Terra and GPT-5.6 Luna outperform Fable 5 at around one-sixteenth the cost. Amusingly, one self-reported benchmark that Fable 5 crushed the GPT-5.6 family on was SWE-Bench Pro, where Fable 5 got 80% compared to GUT-5.6 Sol getting 64.6%. This may help explain why OpenAI chose to publish this article yesterday specifically calling out SWE-Bench Pro for problems they found while auditing that benchmark: In light of these results, we estimate that ~30% of SWE-bench Pro tasks are broken, and advise that model developers carefully examine results I've had some early access to GPT-5.6 Sol - it's definitely very competent, though so far it hasn't struck me as better than Fable at the kind of complex coding tasks I've been using with Anthropic's model. As usual, the model guidance for using GPT-5.6 has the most interesting details. There are a bunch of new API features that I need to explore (and probably add support for in LLM), including: Programmatic Tool Calling allows the models to "compose and run JavaScript that orchestrates tool calls" - which sounds to me like it could help bridge the gap between MCPs and full terminal sessions that can compose CLI utilities in useful ways. Also reminiscent of the dynamic filtering mechanism Anthropic added to their web search tool, which allows code execution against web results as part of a single model turn. Multi-agent lets the model "spin up subagents for parallel, focused work" - the sub-agent pattern now baked into the core API. Prompt cache breakpoints brings the Claude model of prompt caching to OpenAI, letting you be explicit about where the cache breakpoints are rather than relying on the API to detect them automatically. Personally I much prefer automatic detection (still supported by OpenAI), but presumably there are optimization cost savings to be had here if you put the work in. You can now set detail: original on image requests to avoid resizing the image at all before it is processed. Here's a full page with 18 different pelicans - for reasoning efforts none, low, medium, high, xhigh, and max across the three different models. It also lists their token and calculated costs - the least expensive was gpt-5.6-luna at effort none for 0.71 cents, the most expensive was gpt-5.6-sol at max reasoning level for 48.55 cents. In further pelican news, if you jump to 17:50 in their livestream from this morning you'll see OpenAI's own demo of 3D pelicans riding a tricycle, a bicycle, a pony, and another pelican! Tags: ai, openai, generative-ai, llms, llm-tool-use, llm-pricing, pelican-riding-a-bicycle, llm-release, gpt-5

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_3d8f58ac8bbfa71493936d81