GPT-5.6 Luna · Agents’ Last Exam(55 professional fields; exact task version unspecified) 36.1% · 主文证据(ev-gpt56-luna-article-chart-agents-last-exam-medium)

GPT-5.6 Luna 的 Agents’ Last Exam · 55 professional fields; exact task version unspecified 官方出处。GPT-5.6 Luna (medium) · 36.1%。见《GPT-5.6: Frontier intelligence that scales with your ambition | OpenAI》Official GPT-5.6 article interactive chart “Agents' Last Exam” / exact point aria label / GPT-5.6 Luna / effort Medium。证据 ev-gpt56-luna-article-chart-agents-last-exam-medium。

原文与定位

GPT-5.6 Luna · Agents’ Last Exam(55 professional fields; exact task version unspecified),GPT-5.6 Luna (medium)配置,Score 36.1%(具体成绩公布时间未确认)。见《GPT-5.6: Frontier intelligence that scales with your ambition | OpenAI》Official GPT-5.6 article interactive chart “Agents' Last Exam” / exact point aria label / GPT-5.6 Luna / effort Medium。 查看成绩条件

x_value: 57; score: 0.36; model: GPT-5.6 Luna; juice_index: 2; Model: GPT-5.6 Luna; Effort Level: Medium; API cost (USD): $57; Score: 36.1%
官方材料
GPT-5.6: Frontier intelligence that scales with your ambition | OpenAI
定位
主文 · Official GPT-5.6 article interactive chart “Agents' Last Exam” / exact point aria label / GPT-5.6 Luna / effort Medium
材料版本
Official GPT-5.6 article page cache; page date label 2026-07-09, with later price updates dated 2026-07-30 and 2026-08-21. The 2026-11-09 browser capture includes the article tables and interactive chart labels; the chart-state disclosure date is not stated.
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

GPT-5.6 Luna · Agents’ Last Exam(55 professional fields; exact task version unspecified),GPT-5.6 Luna (medium)配置,Score 36.1%(具体成绩公布时间未确认)。官方出处 GPT-5.6: Frontier intelligence that scales with your ambition | OpenAI(主文,Official GPT-5.6 article page cache; page date label 2026-07-09, with later price updates dated 2026-07-30 and 2026-08-21. The 2026-11-09 browser capture includes the article tables and interactive chart labels; the chart-state disclosure date is not stated.)Official GPT-5.6 article interactive chart “Agents' Last Exam” / exact point aria label / GPT-5.6 Luna / effort Medium,https://openai.com/index/gpt-5-6/。Benchlog https://benchlog.lekshome.cc/evidence/gpt-5-6-luna/ev-gpt56-luna-article-chart-agents-last-exam-medium/

关联成绩与条件

GPT-5.6 Luna · Agents’ Last Exam 成绩与配置
指标与成绩配置与评测条件证据关系
Score36.1%原文 36.1% · 单位 %
公布 未确认
GPT-5.6 Luna (medium)
设置
GPT-5.6 Luna; reasoning effort Medium as directly labeled on the official chart.
未知项
Per-benchmark sampling and chart harness settings are not stated.
工具
工具条件未记录
推理预算
Medium
框架
未记录
协议
Agents' Last Exam; version unspecified in the chart; score as displayed.
条件
GPT-5.6 Luna; reasoning effort Medium directly labeled by the chart. Chart x-axis API cost: $57. Other run settings are not stated.

直接支持该成绩

在排名中查看此成绩