English(EN) StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean

新的StochBench基准测试LLM在随机过程上的表现 · 跟踪1个来源

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员推出StochBench，这是一个旨在评估大型语言模型在随机过程复杂问题上能力的新基准。该基准包含450个研究生级别的难题，旨在比侧重于竞赛数学的现有基准更能代表领域特定的应用数学。一个使用Opus 4.8的代理在15分钟/题的时间限制内，在StochBench上达到了34.9%的证明率。 AI

影响该基准有望推动LLM在专业数学推理和形式验证方面的能力改进。

排序理由该条目描述了一个用于评估LLM在特定领域（随机过程）上能力的新基准，属于研究范畴。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了一个用于评估LLM在特定领域（随机过程）上能力的新基准，属于研究范畴。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Idan Davidovich, Debargha Ganguly, Vikash Singh, Vipin Chaudhary · 2026-09-10 04:00

StochBench：精益中随机过程的领域特定基准测试

arXiv:2609.09264v1 Announce Type: new Abstract: Leading benchmarks for formal theorem proving with large language models are small collections drawn from competition math, such as the IMO and Putnam, that poorly represent field-specific applications. We introduce StochBench, a Le…

本文如何被排名

报道来源 [1]

StochBench：精益中随机过程的领域特定基准测试

相关实体

相关话题