GPT-6 Luna · 官方评测披露

GPT-6 Luna 当前收录 10 项测试的官方记录。已完成列明材料的核查。

模型发布 · GPT Luna

官方材料与核查范围

The official release material and current GPT-6.1 Sol addendum HTML/PDF were read in full; the PDF extraction contains 48 physical pages including the title page (47 content pages). Relevant HealthBench comparisons were retained and safety studies were excluded from regular results. All current sources are complete; launch-history review remains separate. 核对时间 。

当前资料不足以还原首发。 没有可核实的首发页面快照;当前网页不能还原 GPT-6 Luna 首发披露全集。

  • 隆重推出 GPT-6 Sol 和 Luna | OpenAI · 主文 · Current article text and interactive AutomationBench point labels captured; current page revision date unknown.
    公布 未确认 · 采集 · 已核查 全文和 AutomationBench 图表标签已核读;其他安全和干预数据排除。
  • Addendum to GPT-6 Astra System Card: GPT-6.1 Sol · 附件 · Official HTML addendum; Table 7 read for HealthBench values, other sections not fully reviewed.
    公布 未确认 · 采集 · 已核查 Current GPT-6.1 Sol addendum HTML and PDF were read in full; the PDF extraction contains 48 physical pages including the title page (47 content pages), and all pages/figures were checked. Relevant HealthBench comparison rows were checked; safety/alignment/monitoring studies were read but excluded from regular results.
  • Addendum to GPT-6 Astra System Card: GPT-6.1 Sol (PDF) · 附件 · 47-page PDF; full text extracted, Table 7 read for HealthBench values, remaining sections not fully reviewed.
    公布 未确认 · 采集 · 已核查 Current GPT-6.1 Sol addendum HTML and PDF were read in full; the PDF extraction contains 48 physical pages including the title page (47 content pages), and all pages/figures were checked. Relevant HealthBench comparison rows were checked; safety/alignment/monitoring studies were read but excluded from regular results.
  • OpenAI News RSS · 主文 · Current RSS; item confirms the official release publication date.
    公布 未确认 · 采集 · 已核查 OpenAI RSS 项目日期为 2026-09-22;用于确认发布日期,不证明该页当前全部内容均在首发时存在。
  • Introducing GPT-6.1 Terra | OpenAI · 主文 · Official GPT-6.1 Terra comparison article, published 2026-10-26; all six charts reviewed and exact chart points cross-checked against official SVG aria-labels and embedded Vega values (143/143). Factuality set/version and sample size are unspecified.
    公布 · 采集 · 已核查 Full article body and all six charts reviewed; exact points for this model were read from the official chart data and aria-label evidence.

配置

  • GPT-6 Luna low · GPT-6 Luna; reasoning effort low as directly labeled in the official chart. low
  • GPT-6 Luna medium · GPT-6 Luna; reasoning effort medium as directly labeled in the official chart. medium
  • GPT-6 Luna high · GPT-6 Luna; reasoning effort high as directly labeled in the official chart. high
  • GPT-6 Luna xhigh · GPT-6 Luna; reasoning effort xhigh as directly labeled in the official chart. xhigh
  • GPT-6 Luna max · GPT-6 Luna; reasoning effort max as directly labeled in the official chart. max
  • GPT-6 Luna, system-card comparison configuration unspecified · GPT-6 Luna; system-card comparison table does not identify reasoning effort or serving configuration.
    未知项 Reasoning effort not stated、Sampling and tool settings not stated

直接前代与后续发布

直接前代 GPT-5.6 Luna。 官方关系依据

官方称 GPT-6 Sol 和 Luna 为你熟悉并已在使用的模型带来智能升级;定价表将 GPT-6 Luna 与 GPT-5.6 Luna 对照。
2 项披露延续 · 8 项新增 · 22 项本次未见 · 0 项待核查
GPT-5.6 Luna 与 GPT-6 Luna 的披露变化
测试已核查状态GPT-5.6 LunaGPT-6 Luna
AutomationBench · 1.0.6; 47 tools; chart-reported score, scoring rule unspecified新增—本次记录
DeepSWE · v1.1延续

已记录的评测条件有变化

前代记录本次记录
HealthBench Professional · 525 physician-authored conversations延续

来源位置 main → attachment

已记录的评测条件有变化

前代记录本次记录
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations新增—本次记录
HealthBench Hard · System-card evaluation; exact dataset version unspecified新增—本次记录
HealthBench Consensus · System-card evaluation; exact dataset version unspecified新增—本次记录
Agents’ Last Exam · V1; 55 subfields; exact task snapshot unspecified新增—本次记录
MMMU-Pro · Vision format explicitly labeled by the official comparison chart; task release/version unspecified新增—本次记录
OSWorld · 2.1 offline set; task count and exact task release unspecified in the selected GPT-6.1 Terra article/chart新增—本次记录
Factual error rate on difficult prompts · Internal error-inducing prompts in the GPT-6.1 Terra comparison article; exact dataset version, sample size and user-flagged provenance unspecified.新增—本次记录
Agents’ Last Exam · 55 professional fields; exact task version unspecified本次未见前代记录—
GDPval-AA · v2本次未见前代记录—
Big Finance Bench · Version and task protocol unspecified本次未见前代记录—
Artificial Analysis Intelligence Index · v4.1本次未见前代记录—
Artificial Analysis Coding Agent Index · v1.1本次未见前代记录—
SWE-Bench Pro · Subset/version unspecified in source本次未见前代记录—
Terminal-Bench · 2.1; source metric reported as score percentage本次未见前代记录—
GeneBench Pro · Version unspecified in source本次未见前代记录—
LifeSciBench · Version unspecified in source本次未见前代记录—
OSWorld · 2.0; subset and scoring details unspecified本次未见前代记录—
BrowseComp · 1,266 题;单代理与多代理按协议区分本次未见前代记录—
BenchCAD · Task version and scoring details unspecified本次未见前代记录—
BenchCAD · Task version unspecified; Python tool protocol本次未见前代记录—
MMMU-Pro · Standard and Vision formats本次未见前代记录—
MMMU-Pro · Tool-enabled protocol; exact version unspecified (gpt56-mmmu-pro-with-tools)本次未见前代记录—
GDP.pdf · 100 professional PDFs and prompts本次未见前代记录—
GPQA Diamond · 198-question Diamond subset本次未见前代记录—
FrontierMath · Tier 1–3 v2本次未见前代记录—
FrontierMath · Tier 4 v2本次未见前代记录—
Toolathlon · Version, subset, and metric unspecified in the 2026-07-09 article本次未见前代记录—
ARC-AGI-3 · Version/subset unspecified in source本次未见前代记录—
AutomationBench · Zapier 私有 early-access set;版本未注明本次未见前代记录—

测试记录 · 10