GPT-5 · GPQA Diamond(198-question Diamond subset) 88.4% · 主文证据(ev-gpt5-pro-gpqa)

GPT-5 的 GPQA Diamond · 198-question Diamond subset 官方出处。GPT-5 Pro · 88.4%。见《隆重推出 GPT-5 | OpenAI》Model evaluations paragraph / GPT-5 Pro。证据 ev-gpt5-pro-gpqa。

原文与定位

GPT-5 · GPQA Diamond(198-question Diamond subset),GPT-5 Pro配置,Accuracy 88.4%(具体成绩公布时间未确认)。见《隆重推出 GPT-5 | OpenAI》Model evaluations paragraph / GPT-5 Pro。 查看成绩条件

With GPT-5 Pro's extended reasoning capabilities, the model sets a new record on GPQA, scoring 88.4% without tools.
官方材料
隆重推出 GPT-5 | OpenAI
定位
主文 · Model evaluations paragraph / GPT-5 Pro
材料版本
Official release article, current page read in browser; revision date unknown; Original page date label 2025-08-07; current page revision date is unknown.
版本公布
未确认
披露时间
未确认 · 首发/后补未确认
采集时间
历史依据
Actual launch-day consumer article HTTP 200 HTML captures 20250807174456 and 20250807174557 saved locally and read in full; not all external image/resource historical bytes verified. See 2026-11-16-review-gpt-early/REPORT.md.
引用文本

GPT-5 · GPQA Diamond(198-question Diamond subset),GPT-5 Pro配置,Accuracy 88.4%(具体成绩公布时间未确认)。官方出处 隆重推出 GPT-5 | OpenAI(主文,Official release article, current page read in browser; revision date unknown; Original page date label 2025-08-07; current page revision date is unknown.)Model evaluations paragraph / GPT-5 Pro,https://openai.com/zh-Hans-CN/index/introducing-gpt-5/。Benchlog https://benchlog.lekshome.cc/evidence/gpt-5/ev-gpt5-pro-gpqa/

关联成绩与条件

GPT-5 · GPQA Diamond 成绩与配置
指标与成绩配置与评测条件证据关系
Accuracy88.4%原文 88.4% · 单位 %
公布 未确认
GPT-5 Pro
设置
ChatGPT variant with extended reasoning; official article reports a no-tools GPQA result.
未知项
Exact reasoning effort and evaluation harness are not stated for the GPQA figure.
工具
禁止工具
推理预算
未记录
框架
未记录
协议
GPQA; no tools.
条件
GPT-5 Pro extended reasoning. Exact effort and harness are not stated.

直接支持该成绩

在排名中查看此成绩