GPT-6.1 Terra · Terminal-Bench(4.0) 50.3% · 主文证据(ev-gpt61-terra-terminal-bench-4-max)

GPT-6.1 Terra 的 Terminal-Bench · 4.0 官方出处。GPT-6.1 Terra max · 50.3%。见《Introducing GPT-6.1 Terra | OpenAI》A significant step up on factuality and coding / Terminal-Bench 4.0 paragraph。证据 ev-gpt61-terra-terminal-bench-4-max。

原文与定位

GPT-6.1 Terra · Terminal-Bench(4.0),GPT-6.1 Terra max配置,Score 50.3%(具体成绩公布时间未确认)。见《Introducing GPT-6.1 Terra | OpenAI》A significant step up on factuality and coding / Terminal-Bench 4.0 paragraph。 查看成绩条件

At maximum reasoning effort, GPT-6.1 Terra solves 50.3% of tasks.
官方材料
Introducing GPT-6.1 Terra | OpenAI
定位
主文 · A significant step up on factuality and coding / Terminal-Bench 4.0 paragraph
材料版本
Official GPT-6.1 Terra article; body and all six interactive charts reviewed; exact chart points cross-checked against official SVG aria-labels and embedded Vega values (143/143). The chart's launch-day inclusion is not verified.
版本公布
披露时间
未确认 · 首发/后补未确认
采集时间
历史依据
Wayback CDX has 2026-10-26 captures with HTTP 200. The 19:49:19Z replay was actually read (HTTP 200) and preserves the Terminal-Bench 4.0 max score in article prose; its interactive charts are empty. The earlier 18:05:14Z replay attempt returned HTTP 429.
引用文本

GPT-6.1 Terra · Terminal-Bench(4.0),GPT-6.1 Terra max配置,Score 50.3%(具体成绩公布时间未确认)。官方出处 Introducing GPT-6.1 Terra | OpenAI(主文,Official GPT-6.1 Terra article; body and all six interactive charts reviewed; exact chart points cross-checked against official SVG aria-labels and embedded Vega values (143/143). The chart's launch-day inclusion is not verified.)A significant step up on factuality and coding / Terminal-Bench 4.0 paragraph,https://openai.com/index/introducing-gpt-6-1-terra/。Benchlog https://benchlog.lekshome.cc/evidence/gpt-6-1-terra/ev-gpt61-terra-terminal-bench-4-max/

关联成绩与条件

GPT-6.1 Terra · Terminal-Bench 成绩与配置
指标与成绩配置与评测条件证据关系
Score50.3%原文 50.3% · 单位 %
公布 未确认
GPT-6.1 Terra max
设置
GPT-6.1 Terra at maximum reasoning effort, as stated in the release article for Terminal-Bench 4.0.
未知项
Other sampling and harness settings are not disclosed in the release article.
工具
工具条件未记录
推理预算
maximum
框架
未记录
协议
Terminal-Bench 4.0; y metric Score; x axis Cost (USD).
条件
GPT-6.1 Terra at maximum reasoning effort, as stated in the release article. Additional later comparison chart cost: $1.84 (USD axis).

直接支持该成绩

在排名中查看此成绩