Gemini 3 Pro · Humanity's Last Exam(2,500-question benchmark) 37.5% · 主文证据(main-hle-no-tools-launch)

Gemini 3 Pro 的 Humanity's Last Exam · 2,500-question benchmark 官方出处。Gemini 3 Pro API default · 37.5%。见《A new era of intelligence with Gemini 3 — launch-day article》Release article / State-of-the-art reasoning paragraph。证据 main-hle-no-tools-launch。

原文与定位

Gemini 3 Pro · Humanity's Last Exam(2,500-question benchmark),Gemini 3 Pro API default配置,Accuracy 37.5%(具体成绩公布时间未确认)。见《A new era of intelligence with Gemini 3 — launch-day article》Release article / State-of-the-art reasoning paragraph。 查看成绩条件

top scores on Humanity's Last Exam (37.5% without the usage of any tools)
官方材料
A new era of intelligence with Gemini 3 — launch-day article
定位
主文 · Release article / State-of-the-art reasoning paragraph
材料版本
Official article archived 2025-11-18 16:07:15 UTC; includes independently recovered launch-day benchmark images.
版本公布
披露时间
· 已有首发依据
采集时间
历史依据
实际取得官方主文首发当天历史回放 https://web.archive.org/web/20251118160715id_/https://blog.google/products/gemini/gemini-3/;Memento-Datetime Tue, 18 Nov 2025 16:07:15 GMT。主表与 Deep Think 图同日16:08:44回放、Vending-Bench图同日16:09:03回放均已下载并视觉核查,不依赖现行图像字节。
引用文本

Gemini 3 Pro · Humanity's Last Exam(2,500-question benchmark),Gemini 3 Pro API default配置,Accuracy 37.5%(具体成绩公布时间未确认)。官方出处 A new era of intelligence with Gemini 3 — launch-day article(主文,Official article archived 2025-11-18 16:07:15 UTC; includes independently recovered launch-day benchmark images.)Release article / State-of-the-art reasoning paragraph,https://blog.google/products/gemini/gemini-3/。Benchlog https://benchlog.lekshome.cc/evidence/gemini-3-pro/main-hle-no-tools-launch/

关联成绩与条件

Gemini 3 Pro · Humanity's Last Exam 成绩与配置
指标与成绩配置与评测条件证据关系
Accuracy37.5%原文 37.5% · 单位 %
公布 未确认
Gemini 3 Pro API default
设置
Gemini API model id gemini-3-pro-preview; default sampling settings. Gemini results are pass@1 and single-attempt unless specified; smaller benchmarks average multiple trials.
未知项
The evaluation table does not specify a thinking budget or inference-time compute setting.
工具
禁止工具
推理预算
未记录
框架
未记录
协议
No tools; academic reasoning full set.
条件
Gemini API model gemini-3-pro-preview; default sampling settings; pass@1 unless stated otherwise.

直接支持该成绩

在排名中查看此成绩