MathVista
MathVista evaluates mathematical reasoning of foundation models in visual contexts. It consists of 6,141 examples derived from 28 existing multimodal datasets and 3 newly created datasets (IQTest, FunctionQA, and PaperQA), combining challenges from diverse mathematical and visual tasks to assess models' ability to understand complex figures and perform rigorous reasoning.
o3 from OpenAI currently leads the MathVista leaderboard with a score of 0.868 across 36 evaluated AI models.
o3 leads with 86.8%, followed by o4-mini at 84.3% and 
Step3-VL-10B at 84.0%.
Progress Over Time
Interactive timeline showing model performance evolution on MathVista
MathVista Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | OpenAI | — | — | — | ||
| 2 | OpenAI | — | — | — | ||
| 3 | StepFun | 10B | — | — | ||
| 4 |  Moonshot AI | — | — | — | ||
| 5 |  Meta | 400B | — | — | ||
| 6 | OpenAI | — | 1.0M | $0.40 / $1.60 | ||
| 7 | OpenAI | — | — | — | ||
| 8 | OpenAI | — | 1.0M | $2.00 / $8.00 | ||
| 9 | OpenAI | — | — | — | ||
| 10 |  Alibaba Cloud / Qwen Team | 73B | — | — | ||
| 11 | Meta | 109B | — | — | ||
| 12 |  Mistral AI | 124B | — | — | ||
| 13 |  xAI | — | — | — | ||
| 14 |  Google | — | — | — | ||
| 14 | xAI | — | — | — | ||
| 16 | Alibaba Cloud / Qwen Team | 7B | — | — | ||
| 17 |  Anthropic | — | — | — | ||
| 18 | Mistral AI | 24B | — | — | ||
| 19 | Google | — | — | — | ||
| 20 | OpenAI | — | 128K | $2.50 / $10.00 | ||
| 21 |  DeepSeek | 27B | — | — | ||
| 22 |  Microsoft | 6B | — | — | ||
| 23 | OpenAI | — | 128K | $2.50 / $10.00 | ||
| 24 | DeepSeek | 16B | — | — | ||
| 25 | Mistral AI | 12B | — | — | ||
| 26 | 90B | — | — | |||
| 27 | OpenAI | — | — | — | ||
| 28 | OpenAI | — | 1.0M | $0.10 / $0.40 | ||
| 29 | Google | 8B | — | — | ||
| 30 | DeepSeek | 3B | — | — | ||
| 31 | xAI | — | — | — | ||
| 31 | xAI | — | — | — | ||
| 33 | 11B | — | — | |||
| 34 | Google | — | — | — | ||
| 35 | Microsoft | 4B | — | — | ||
| 36 | OpenAI | — | 16K | $0.50 / $1.50 |
FAQ
Common questions about MathVista.
More evaluations to explore
Related benchmarks in the same category
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions
MATH dataset contains 12,500 challenging competition mathematics problems from AMC 10, AMC 12, AIME, and other mathematics competitions. Each problem includes full step-by-step solutions and spans multiple difficulty levels (1-5) across seven mathematical subjects including Prealgebra, Algebra, Number Theory, Counting and Probability, Geometry, Intermediate Algebra, and Precalculus.
MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning. Contains 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering across 30 subjects and 183 subfields.