math benchmark
MathVista-Mini
MathVista-Mini is a smaller version of the MathVista benchmark that evaluates mathematical reasoning in visual contexts. It consists of examples derived from multimodal datasets involving mathematics, combining challenges from diverse mathematical and visual tasks to assess foundation models' ability to solve problems requiring both visual understanding and mathematical reasoning.
Updated Aug 7, 2026
Published models23
Registry coverage23
MetricScore
EvidenceB
MathVista-Mini leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
Score distribution
Top published rows on the benchmark's original scale.
MathVista-Mini highlights
The top published results on this benchmark's own scale.
What is MathVista-Mini?
Definition and scoring fields from the benchmark registry.
MathVista-Mini is a smaller version of the MathVista benchmark that evaluates mathematical reasoning in visual contexts. It consists of examples derived from multimodal datasets involving mathematics, combining challenges from diverse mathematical and visual tasks to assess foundation models' ability to solve problems requiring both visual understanding and mathematical reasoning.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MathVista-Mini
- Modality
- multimodal
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mathvista-mini|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MathVista-Mini.
Which model scores highest on MathVista-Mini?
Kimi K2.5 is currently ranked first with 90.1%.
What does MathVista-Mini measure?
MathVista-Mini is a smaller version of the MathVista benchmark that evaluates mathematical reasoning in visual contexts. It consists of examples derived from multimodal datasets involving mathematics, combining challenges from diverse mathematical and visual tasks to assess foundation models' ability to solve problems requiring both visual understanding and mathematical reasoning.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
23 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.