GPT-5.1 · MLE-Bench(30 competition subset selected from tasks with <50GB data and <10h reference duration) 12% · 附件证据(ev-gpt51-later-mlebench-card)
GPT-5.1 的 MLE-Bench · 30 competition subset selected from tasks with <50GB data and <10h reference duration 官方出处。Codex-Max system-card later comparison · 12%。见《GPT-5.1-Codex-Max System Card PDF (later GPT-5.1 comparisons)》Official System Card PDF p.23, Figure 12; numeric bar label visually inspected。证据 ev-gpt51-later-mlebench-card。
原文与定位
GPT-5.1 · MLE-Bench(30 competition subset selected from tasks with <50GB data and <10h reference duration),Codex-Max system-card later comparison配置,Bronze pass@1 12%(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.23, Figure 12; numeric bar label visually inspected。 查看成绩条件
Figure 12: gpt-5.1 (no browsing): 12%. MLE-bench-30 selected subset; <50GB data and <10h reference-task filter; bronze pass@1; agent has a GPU and Kaggle data. Generic environment description allows 24h and some 100h experiments; exact per-model duration unspecified.
- 官方材料
- GPT-5.1-Codex-Max System Card PDF (later GPT-5.1 comparisons) · PDF 第 23 页
- 定位
- 附件 · Official System Card PDF p.23, Figure 12; 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 · MLE-Bench(30 competition subset selected from tasks with <50GB data and <10h reference duration),Codex-Max system-card later comparison配置,Bronze pass@1 12%(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.23, Figure 12; numeric bar label visually inspected,https://cdn.openai.com/pdf/2a7d98b1-57e5-4147-8d0e-683894d782ae/5p1_codex_max_card_03.pdf#page=23。Benchlog https://benchlog.lekshome.cc/evidence/gpt-5-1/ev-gpt51-later-mlebench-card/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Bronze pass@112%原文 12% · 单位 % 公布 未确认 | Codex-Max system-card later comparison
| 直接支持该成绩 在排名中查看此成绩 |