PulseAugur
EN
LIVE 09:54:35

New Chart2Code benchmark reveals GPT-5 struggles with multimodal tasks

By PulseAugur Editorial · [2 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 2 sources. How we write summaries →

New Chart2Code benchmark reveals GPT-5 struggles with multimodal tasks

How we ranked this

Signal score
1 / 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
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
1 days old
Coverage has settled into its steady-state source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Jihan Yao, Yushi Hu, Wenyuan Wang, Bin Han, Shangbin Feng, Guang Yang, Yujie Yi, Bingbing Wen, Ranjay Krishna, Lucy Lu Wang, Yulia Tsvetkov, Noah A. Smith, Banghua Zhu ·

    MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation

    arXiv:2505.17613v2 Announce Type: replace Abstract: Automatically evaluating multimodal generation presents a significant challenge, as automated metrics often struggle to align with human evaluation, especially for complex tasks that involve multiple modalities. We present MMMG,…

  2. 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