PulseAugur
EN
LIVE 06:58:52

New Chart2Code benchmark reveals GPT-5 struggles with multimodal tasks

By PulseAugur Editorial · [1 sources] ·

A new benchmark called Chart2Code has been introduced to evaluate the chart understanding and code generation capabilities of large multimodal models (LMMs). This benchmark features a hierarchical structure with three levels of increasing difficulty, designed to reflect real-world user scenarios. Chart2Code comprises 2,023 tasks across 22 chart types and includes metrics for code correctness and visual fidelity. Initial testing on 25 state-of-the-art LMMs, including GPT-5, revealed significant challenges, with GPT-5 achieving an average score of only 0.57 on code evaluation and 0.22 on chart quality for editing tasks. AI

IMPACT This benchmark's difficulty highlights current limitations in multimodal reasoning, potentially guiding future LMM development towards better chart understanding and code generation.

RANK_REASON New academic paper introducing a novel benchmark for evaluating multimodal models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New Chart2Code benchmark reveals GPT-5 struggles with multimodal tasks

How we ranked this

Signal score
25 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
New academic paper introducing a novel benchmark for evaluating multimodal models. [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.

Full methodology in our editorial standards.

COVERAGE [1]

  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 ·

    From Charts to Code: A Hierarchical Benchmark for Multimodal Models

    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…

RELATED ENTITIES

RELATED TOPICS