GPT-6.1 Sol · 官方评测披露

GPT-6.1 Sol 当前收录 15 项测试的官方记录。已完成列明材料的核查。

模型发布 · GPT Sol

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。 没有首发页面历史快照,无法证明当前结果集与首发时完全一致。

  • 推出 GPT-6.1 Sol | OpenAI · 主文 · Current article text and six interactive chart point-label captures; current page revision date unknown.
    公布 未确认 · 采集 · 已核查 正文与六组常规能力图表均已检查;精确 tooltip 按模型、effort、精确 score 去重,未用图中取整分。安全与成本曲线不入候选。
  • 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.
  • GPT-6.1 Sol Model | OpenAI API · 主文 · Current API model page; confirms public model ID and supported reasoning.effort settings; page revision date unknown.
    公布 未确认 · 采集 · 已核查 确认公开模型 ID gpt-6.1-sol 及页面列明的 reasoning.effort 支持范围;不将模型文档当成绩证据。
  • 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 2026-09-29;用于确认发布日期,不证明当前网页全部内容均属于首发版本。
  • 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-6.1 Sol low · GPT-6.1 Sol; reasoning effort low as directly labeled in the official chart. low
  • GPT-6.1 Sol medium · GPT-6.1 Sol; reasoning effort medium as directly labeled in the official chart. medium
  • GPT-6.1 Sol high · GPT-6.1 Sol; reasoning effort high as directly labeled in the official chart. high
  • GPT-6.1 Sol xhigh · GPT-6.1 Sol; reasoning effort xhigh as directly labeled in the official chart. xhigh
  • GPT-6.1 Sol max · GPT-6.1 Sol; reasoning effort max as directly labeled in the official chart. max
  • GPT-6.1 Sol, system-card configuration unspecified · GPT-6.1 Sol; 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-6 Sol。 官方关系依据

我们推出了 GPT-6.1 Sol,这是 GPT-6 Sol 的升级版。
11 项披露延续 · 4 项新增 · 0 项本次未见 · 0 项待核查
GPT-6 Sol 与 GPT-6.1 Sol 的披露变化
测试已核查状态GPT-6 SolGPT-6.1 Sol
DeepSWE · v1.1延续

已记录的评测条件有变化

前代记录本次记录
GDP.pdf · OpenAI 2026-09 chart; 10 professional domains; chart score, scoring rule and exact set version unspecified延续

已记录的评测条件有变化

前代记录本次记录
AutomationBench · 1.0.6; 47 tools; chart-reported score, scoring rule unspecified延续

已记录的评测条件有变化

前代记录本次记录
OSWorld · 2.0 v2026.08.08 offline set; partial reward score延续

已记录的评测条件有变化

前代记录本次记录
Terminal-Bench-Science · 0.1延续

已记录的评测条件有变化

前代记录本次记录
User-flagged factuality, high-difficulty prompts · Anonymized ChatGPT conversations previously flagged by users for factual errors; exact set version and sample size unspecified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

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延续

已记录的评测条件有变化

前代记录本次记录
HealthBench Hard · System-card evaluation; exact dataset version unspecified延续

已记录的评测条件有变化

前代记录本次记录
HealthBench Consensus · System-card evaluation; exact dataset version unspecified延续

已记录的评测条件有变化

前代记录本次记录
Agents’ Last Exam · V1; 55 subfields; exact task snapshot unspecified延续

已记录的评测条件有变化

前代记录本次记录
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
Terminal-Bench · 4.0新增—本次记录

测试记录 · 15