{
  "schema_version": 1,
  "id": "evt-2023-mathvista",
  "slug": "mathvista-visual-math-benchmark",
  "title": {
    "en": "MathVista establishes a benchmark for mathematical reasoning in visual contexts",
    "zh-CN": "MathVista 建立视觉场景中的数学推理评测基准"
  },
  "dates": {
    "event": "2023-10-03",
    "first_public_claim": "2023-10-03",
    "paper_release": "2023-10-03",
    "artifact_release": null,
    "independently_verified": null,
    "added_to_chronicle": "2026-09-11",
    "last_updated": "2026-09-11"
  },
  "event_types": [
    "benchmark",
    "dataset"
  ],
  "significance": {
    "tier": "H2",
    "rationale": {
      "en": "MathVista made mathematical reasoning in visual contexts a dedicated evaluation target, consolidating diagrams, charts, geometry, scientific figures and other multimodal tasks into a large benchmark before multimodal mathematical evaluation became a standard capability axis.",
      "zh-CN": "MathVista 将视觉场景中的数学推理确立为独立评测目标，把图表、几何图形、科学图像等多模态任务整合成大规模基准，早于多模态数学评测成为通用能力维度。"
    }
  },
  "mathematical_novelty": {
    "type": "tooling_only"
  },
  "interfaces": [
    "informal",
    "symbolic",
    "numeric"
  ],
  "claim": {
    "en": "MathVista introduced 6,141 visual mathematical-reasoning examples drawn from 28 existing multimodal datasets and three newly created datasets, and used them to systematically evaluate 12 foundation models across mathematical and visual task types.",
    "zh-CN": "MathVista 引入 6,141 个视觉数学推理样例，来源包括 28 个既有多模态数据集和 3 个新建数据集，并据此系统评测 12 个基础模型在不同数学与视觉任务上的能力。"
  },
  "summary": {
    "en": "The benchmark combines visual perception with compositional mathematical reasoning. The initial study found a substantial gap between frontier multimodal models and human performance, while the public project provides dataset access, evaluation code and model-result tooling.",
    "zh-CN": "该基准把视觉感知与组合式数学推理结合起来。初始研究显示前沿多模态模型与人类表现之间仍有明显差距，公开项目同时提供数据访问、评测代码与模型结果工具。"
  },
  "why_it_matters": {
    "en": "It broadened AI4Math evaluation beyond text-only word problems and formal statements, creating a reference point for later multimodal and Olympiad-level benchmarks that require models to reason over mathematical information embedded in images.",
    "zh-CN": "它把 AI4Math 评测从纯文本文字题和形式陈述扩展到图像中承载的数学信息，为后续多模态与奥赛级评测提供了重要参照。"
  },
  "ai_role": {
    "level": "computation_only",
    "description": {
      "en": "Language and multimodal foundation models were evaluated on visual mathematical-reasoning tasks; the benchmark itself was curated and designed by researchers.",
      "zh-CN": "语言模型与多模态基础模型在视觉数学推理任务上接受评测；基准的数据整理与设计由研究者完成。"
    }
  },
  "human_contribution": {
    "description": {
      "en": "Researchers assembled and normalized datasets, created new visual reasoning tasks, defined the taxonomy and evaluation protocol, and manually analyzed model failure modes and human baselines.",
      "zh-CN": "研究者整理并规范化数据集、创建新的视觉推理任务、定义分类与评测协议，并人工分析模型失败模式和人类基线。"
    }
  },
  "systems": [
    "mathvista"
  ],
  "organizations": [],
  "people": [
    "pan-lu",
    "hritik-bansal",
    "tony-xia",
    "jiacheng-liu"
  ],
  "problems": [
    "visual-mathematical-reasoning"
  ],
  "methods": [
    "multimodal-evaluation",
    "benchmarking",
    "visual-reasoning"
  ],
  "verification": {
    "evidence_level": "E3",
    "status": "paper_released",
    "formal_assurance": "artifact_available",
    "history": [
      {
        "date": "2023-10-03",
        "status": "paper_released",
        "evidence_level": "E2",
        "note": {
          "en": "The arXiv research record introduced MathVista and its initial evaluation of foundation models.",
          "zh-CN": "arXiv 研究记录公开 MathVista，并报告其对基础模型的初始评测。"
        }
      },
      {
        "date": "2026-09-11",
        "status": "paper_released",
        "evidence_level": "E3",
        "note": {
          "en": "The public MathVista repository and project site expose benchmark data access and evaluation tooling. E3 records artifact-level inspectability rather than independent verification of every reported score.",
          "zh-CN": "公开的 MathVista 仓库与项目页面提供基准数据访问和评测工具。E3 表示产物层级可检查，并不等同于所有报告分数都已获得独立验证。"
        }
      }
    ]
  },
  "sources": [
    {
      "id": "arxiv-mathvista-2310.02255",
      "tier": "S1",
      "type": "paper",
      "title": "MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts",
      "url": "https://arxiv.org/abs/2310.02255",
      "primary": true,
      "published_date": "2023-10-03",
      "accessed_at": "2026-09-11"
    },
    {
      "id": "mathvista-project",
      "tier": "S1",
      "type": "other",
      "title": "MathVista project page",
      "url": "https://mathvista.github.io/",
      "primary": true,
      "published_date": null,
      "accessed_at": "2026-09-11"
    },
    {
      "id": "github-mathvista",
      "tier": "S1",
      "type": "repository",
      "title": "MathVista benchmark repository",
      "url": "https://github.com/lupantech/MathVista",
      "primary": true,
      "published_date": null,
      "accessed_at": "2026-09-11"
    }
  ],
  "artifacts": [
    {
      "id": "mathvista-repository",
      "kind": "dataset",
      "title": "MathVista dataset and evaluation code",
      "url": "https://github.com/lupantech/MathVista"
    }
  ],
  "relationships": {
    "predecessors": [
      "evt-2021-math-benchmark"
    ],
    "successors": [
      "evt-2024-olympiadbench"
    ],
    "related": []
  },
  "timeline": {
    "featured": true,
    "significance": "primary"
  },
  "tags": [
    "benchmark",
    "multimodal",
    "visual-reasoning",
    "math-reasoning",
    "dataset"
  ],
  "editorial": {
    "created_at": "2026-09-11",
    "last_reviewed": "2026-09-11",
    "reviewers": [
      "Charlie-Wang-03"
    ]
  },
  "corrections": []
}