MultimodalEst. 2023

MathVista

MathVista evaluates mathematical reasoning in visual contexts by combining math problems with charts, plots, geometry figures, scientific diagrams, and synthetic scenes. It aggregates 6,141 examples from 28 existing datasets and 3 new datasets, covering five task types and seven mathematical reasoning abilities. Models must interpret visual information accurately and apply mathematical reasoning to derive correct answers.

Metrics

Accuracy (%) on visual math reasoning tasks

Created By

Pan Lu et al. (UCLA)

Top Model Scores

RankModelScoreDate
1GPT-5.272.6%2026-03
2Gemini 3 Ultra71.3%2026-01
3Claude Opus 4.669.8%2026-02
4Grok 466.4%2026-02
5Llama 4 405B62.1%2026-01