Gemini 2.5 Pro (GA) · Humanity's Last Exam(2,500-question benchmark) 21.6% · 附件证据(t3-hle)

Gemini 2.5 Pro (GA) 的 Humanity's Last Exam · 2,500-question benchmark 官方出处。Gemini 2.5 Pro stable API · 21.6%。见《Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities》PDF p.13, Table 3, Humanity's Last Exam / no tools row, Gemini 2.5 Pro column。证据 t3-hle。

原文与定位

Gemini 2.5 Pro (GA) · Humanity's Last Exam(2,500-question benchmark),Gemini 2.5 Pro stable API配置,Accuracy 21.6%(具体成绩公布时间未确认)。见《Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities》PDF p.13, Table 3, Humanity's Last Exam / no tools row, Gemini 2.5 Pro column。 查看成绩条件

notools - 4.6% 4.6%† 5.1%† 11.0% 21.6%
官方材料
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities · PDF 第 13 页
定位
附件 · PDF p.13, Table 3, Humanity's Last Exam / no tools row, Gemini 2.5 Pro column
材料版本
73-page PDF; embedded results include Gemini 2.5 Pro GA up to version 06-17; PDF metadata creation 2025-10-16 is not treated as publication date
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
暂无可靠历史版本依据
引用文本

Gemini 2.5 Pro (GA) · Humanity's Last Exam(2,500-question benchmark),Gemini 2.5 Pro stable API配置,Accuracy 21.6%(具体成绩公布时间未确认)。官方出处 Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities(附件,73-page PDF; embedded results include Gemini 2.5 Pro GA up to version 06-17; PDF metadata creation 2025-10-16 is not treated as publication date)PDF p.13, Table 3, Humanity's Last Exam / no tools row, Gemini 2.5 Pro column,https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf#page=13。Benchlog https://benchlog.lekshome.cc/evidence/gemini-2-5-pro/t3-hle/

关联成绩与条件

Gemini 2.5 Pro (GA) · 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
Accuracy21.6%原文 21.6% · 单位 %
公布 未确认
Gemini 2.5 Pro stable API
设置
AI Studio API model id gemini-2.5-pro; default sampling settings. Technical report states Gemini scores are pass@1 and single-attempt unless specified. Aider Polyglot averages 3 trials; SWE-bench uses the internal agentic harness; Vibe-Eval uses Gemini as judge.
未知项
Thinking budget and any non-default settings for individual evaluations are not stated except where noted in each protocol.
工具
禁止工具
推理预算
未记录
框架
未记录
协议
No-tools variant; Scale leaderboard.
条件
Gemini pass@1; single attempt unless stated otherwise.

直接支持该成绩

在排名中查看此成绩