GPT-5.1 · PaperBench(10-paper subset; each paper requires <10GB external data) 34% · 附件证据(ev-gpt51-later-paperbench-card)

GPT-5.1 的 PaperBench · 10-paper subset; each paper requires <10GB external data 官方出处。Codex-Max system-card later comparison · 34%。见《GPT-5.1-Codex-Max System Card PDF (later GPT-5.1 comparisons)》Official System Card PDF p.21, Figure 9; numeric bar label visually inspected。证据 ev-gpt51-later-paperbench-card。

原文与定位

GPT-5.1 · PaperBench(10-paper subset; each paper requires <10GB external data),Codex-Max system-card later comparison配置,Pass@1 34%(具体成绩公布时间未确认)。见《GPT-5.1-Codex-Max System Card PDF (later GPT-5.1 comparisons)》Official System Card PDF p.21, Figure 9; numeric bar label visually inspected。 查看成绩条件

Figure 9: gpt-5.1 (no browsing): 34%. PaperBench 10-paper subset; each requires <10GB external files; pass@1; no browsing. The section reports Extra High reasoning effort.
官方材料
GPT-5.1-Codex-Max System Card PDF (later GPT-5.1 comparisons) · PDF 第 21 页
定位
附件 · Official System Card PDF p.21, Figure 9; numeric bar label visually inspected
材料版本
Current 27-page official PDF dated November 18, 2025; full text pp.1-27 and all tables/figures read. Its GPT-5.1 comparison bars are later disclosures, not GPT-5.1 launch evidence; current revision time unknown.
版本公布
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-5.1 · PaperBench(10-paper subset; each paper requires <10GB external data),Codex-Max system-card later comparison配置,Pass@1 34%(具体成绩公布时间未确认)。官方出处 GPT-5.1-Codex-Max System Card PDF (later GPT-5.1 comparisons)(附件,Current 27-page official PDF dated November 18, 2025; full text pp.1-27 and all tables/figures read. Its GPT-5.1 comparison bars are later disclosures, not GPT-5.1 launch evidence; current revision time unknown.)Official System Card PDF p.21, Figure 9; numeric bar label visually inspected,https://cdn.openai.com/pdf/2a7d98b1-57e5-4147-8d0e-683894d782ae/5p1_codex_max_card_03.pdf#page=21。Benchlog https://benchlog.lekshome.cc/evidence/gpt-5-1/ev-gpt51-later-paperbench-card/

关联成绩与条件

GPT-5.1 · PaperBench 成绩与配置
指标与成绩配置与评测条件证据关系
Pass@134%原文 34% · 单位 %
公布 未确认
Codex-Max system-card later comparison
设置
GPT-5.1 comparison bars in the GPT-5.1-Codex-Max System Card; per-model effort not independently identified.
未知项
比较图没有逐模型明确所有采样与effort设置;不根据对照模型或token预算推定档位。
工具
工具条件未记录
推理预算
Extra High
框架
未记录
协议
PaperBench 10-paper subset; each requires <10GB external files; pass@1; no browsing. The section reports Extra High reasoning effort.
条件
原图明示百分比;未从柱高估数。GPT-5.1对照值属于后续来源。卡片当前修订时点未确认,publishedAt保持null;不混入内部PR/Proof Q&A或风险子任务。

直接支持该成绩

在排名中查看此成绩