English(EN) From Charts to Code: A Hierarchical Benchmark for Multimodal Models

新的Chart2Code基准测试揭示GPT-5在多模态任务上存在困难

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

一项名为Chart2Code的新基准测试已被推出，用于评估大型多模态模型（LMM）的图表理解和代码生成能力。该基准测试具有层级结构，包含三个难度递增的级别，旨在反映真实用户场景。Chart2Code包含2,023个任务，涵盖22种图表类型，并包含代码正确性和视觉保真度的指标。对包括GPT-5在内的25个最先进LMM进行的初步测试显示出显著的挑战，GPT-5在代码评估上的平均得分仅为0.57，在编辑任务的图表质量上的得分仅为0.22。 AI

影响该基准测试的难度凸显了当前多模态推理的局限性，可能指导未来LMM在图表理解和代码生成方面的发展。

排序理由一项介绍用于评估多模态模型的新颖基准测试的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 21 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 一项介绍用于评估多模态模型的新颖基准测试的学术论文。[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, 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]

arXiv cs.AI TIER_1 English(EN) · Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu, Zijian Zhang, Yifei Tao, Dongxing Mao, Yang Wan, Jingru Tan, Min Zeng, Min Li, Alex Jinpeng Wang · 2026-10-01 04:00

从图表到代码：多模态模型的层级基准测试

arXiv:2510.17932v5 Announce Type: replace-cross Abstract: We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturin…

本文如何被排名

报道来源 [1]

从图表到代码：多模态模型的层级基准测试

相关实体

相关话题