MathVista
by UCLA · open-source · Last verified 2026-03-01
Mathematical reasoning benchmark requiring visual understanding of charts, plots, geometry diagrams, and infographics. Tests the intersection of visual perception and mathematical reasoning with 6,141 problems from 28 existing datasets and 3 newly collected ones.
https://mathvista.github.io ↗C+
C+—Average
Adoption: BQuality: AFreshness: ACitations: BEngagement: F
Specifications
- License
- CC-BY-SA-4.0
- Pricing
- open-source
- Capabilities
- model-evaluation, visual-math-testing, chart-understanding-assessment
- Integrations
- lm-eval-harness
- Use Cases
- visual-math-evaluation, chart-understanding-testing, multimodal-reasoning-assessment
- API Available
- No
- Evaluated Models
- claude-4, gpt-5, gemini-2.5-pro
- Metrics
- accuracy, gps-accuracy, math-word-accuracy
- Methodology
- 6,141 visual math problems across geometry, chart reading, and mathematical word problems. Models receive images and questions, evaluated for answer correctness.
- Last Run
- 2026-02-15
- Tags
- benchmark, evaluation, multimodal, math, visual-reasoning
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
58.3Adoption
64
Quality
86
Freshness
84
Citations
62
Engagement
0