math benchmark
MathVerse
MathVerse evaluates multimodal mathematical reasoning, testing whether models genuinely interpret visual math diagrams rather than relying on text.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
MathVerse leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 89.7% | 100.0% | 2 | C | |
| 2 | BY | 89.2% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
MathVerse highlights
The top published results on this benchmark's own scale.
What is MathVerse?
Definition and scoring fields from the benchmark registry.
MathVerse evaluates multimodal mathematical reasoning, testing whether models genuinely interpret visual math diagrams rather than relying on text.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MathVerse
- Modality
- multimodal
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mathverse|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MathVerse.
Which model scores highest on MathVerse?
Seed 2.1 Pro is currently ranked first with 89.7%.
What does MathVerse measure?
MathVerse evaluates multimodal mathematical reasoning, testing whether models genuinely interpret visual math diagrams rather than relying on text.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.