PulseAugur
实时 09:28:57
English(EN) Two years of pelicans on bicycles: 103 SVGs, 66 models, and what the guy who invented the benchmark says about it

LLM基准测试:自行车上的鹈鹕展示了两年来的快速进展

在过去的两年里,Simon Willison 使用了一个独特的基准测试来追踪大型语言模型的进展:生成一个骑自行车的鹈鹕的SVG。最初,模型在处理这项任务时很困难,生成抽象的形状和无意义的解释。然而,到2025年中期,DeepSeek R1和Nvidia的产品等模型显示出显著的改进,有些甚至开始“编辑化”,拒绝提示或添加创意元素。一场使用GPT-4.1 mini作为裁判的比赛揭示了Gemini 2.5 Pro预览版在代码生成和图像合成方面表现出色,凸显了LLM能力的快速发展。 AI

影响 展示了LLM在代码生成和细致任务解释方面的快速进展,可能影响未来的基准测试设计。

排序理由 该项目描述了一个新颖的LLM评估基准测试,并追踪了其随时间的进展,包括具体的模型性能和演变。[lever_c_demoted from research: ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

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

LLM基准测试:自行车上的鹈鹕展示了两年来的快速进展

本文如何被排名

Signal score
30 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目描述了一个新颖的LLM评估基准测试,并追踪了其随时间的进展,包括具体的模型性能和演变。[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
model release, product
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]

  1. dev.to — LLM tag TIER_1 English(EN) · Zhengxin ·

    两年的自行车鹈鹕:103个SVG,66个模型,以及发明基准测试的人对此有何看法

    <p>In October 2024, Simon Willison gave sixteen LLMs the same eight words:</p> <blockquote> <p>Generate an SVG of a pelican riding a bicycle.</p> </blockquote> <p>He has been running it on every new model since. Twenty-three months later there are 103 of these drawings scattered …