GPT-5 nano · FrontierMath(Set/version unspecified in GPT-5 and GPT-5.1 release tables; Python tool enabled.) 9.6% · 主文证据(ev-gpt5-nano-frontiermath-python)

GPT-5 nano 的 FrontierMath · Set/version unspecified in GPT-5 and GPT-5.1 release tables; Python tool enabled. 官方出处。GPT-5 nano (high) · 9.6%。见《Introducing GPT-5 for developers | OpenAI》Detailed benchmarks / FrontierMath (with python tool only), 2025-08-07 21:34:00 UTC archived version。证据 ev-gpt5-nano-frontiermath-python。

原文与定位

GPT-5 nano · FrontierMath(Set/version unspecified in GPT-5 and GPT-5.1 release tables; Python tool enabled.),GPT-5 nano (high)配置,Score 9.6%(成绩公布 2025-08-07)。见《Introducing GPT-5 for developers | OpenAI》Detailed benchmarks / FrontierMath (with python tool only), 2025-08-07 21:34:00 UTC archived version。 查看成绩条件

FrontierMath (with python tool only): GPT-5 (high) 26.3%; GPT-5 mini (high) 22.1%; GPT-5 nano (high) 9.6%.
官方材料
Introducing GPT-5 for developers | OpenAI
定位
主文 · Detailed benchmarks / FrontierMath (with python tool only), 2025-08-07 21:34:00 UTC archived version
材料版本
Official GPT-5 developer release article; launch-day Wayback replay 2025-08-07 21:34:00 UTC, CDX status 200 text/html; detailed benchmark tables read and transcribed. This is the later of two same-day captures with different FrontierMath nano values.
版本公布
披露时间
· 已有首发依据
采集时间
历史依据
Wayback CDX capture 20250807213400, status 200 text/html; replay via http://web.archive.org/web/20250807213400id_/https://openai.com/index/introducing-gpt-5-for-developers/ returned HTTP 200. The archived article is dated August 7, 2025.
引用文本

GPT-5 nano · FrontierMath(Set/version unspecified in GPT-5 and GPT-5.1 release tables; Python tool enabled.),GPT-5 nano (high)配置,Score 9.6%(成绩公布 2025-08-07)。官方出处 Introducing GPT-5 for developers | OpenAI(主文,Official GPT-5 developer release article; launch-day Wayback replay 2025-08-07 21:34:00 UTC, CDX status 200 text/html; detailed benchmark tables read and transcribed. This is the later of two same-day captures with different FrontierMath nano values.)Detailed benchmarks / FrontierMath (with python tool only), 2025-08-07 21:34:00 UTC archived version,https://openai.com/index/introducing-gpt-5-for-developers/。Benchlog https://benchlog.lekshome.cc/evidence/gpt-5-nano/ev-gpt5-nano-frontiermath-python/

关联成绩与条件

GPT-5 nano · FrontierMath 成绩与配置
指标与成绩配置与评测条件证据关系
Score9.6%原文 9.6% · 单位 %
公布

结果冲突待核对,精确排名不采用。

GPT-5 nano (high)
设置
API nano model; benchmark table labels high reasoning effort.
未知项
未另记
工具
允许工具
推理预算
high
框架
未记录
协议
FrontierMath (with python tool only)
条件
API GPT-5 nano; high reasoning effort. 同日17:13版本为72.8%,21:34版本为9.6%;没有明确官方更正依据,两值均不排序。

直接支持该成绩

在排名中查看此成绩