math benchmark
MathVerse Leaderboard
MathVerse evaluates multimodal mathematical reasoning by testing whether models interpret visual math diagrams rather than relying on text.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
MathVerse Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelBY | Score89.70% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelBY | Score89.20% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
MathVerse Highlights
The leading models and scores on this benchmark.
MathVerse Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MathVerse
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MathVerse?
What MathVerse measures and how its scores work.
MathVerse is a math benchmark for multimodal mathematical reasoning.
It measures performance using the Score metric, reported as a ratio, and evaluates interpretation of visual math diagrams.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MathVerse
- Modality
- multimodal
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MathVerse.
Which model scores highest on MathVerse?
Seed 2.1 Pro is currently ranked first with 89.70%.
What are the top three models on MathVerse?
The current leaders are Seed 2.1 Pro (89.70%) and Seed 2.1 Turbo (89.20%).
Which MathVerse model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among MathVerse results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.