math benchmark
MathVerse-Mini
MathVerse-Mini is a subset of the MathVerse benchmark for evaluating math reasoning capabilities in vision-language models.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MathVerse-Mini Ranking
Higher score ranks better on this benchmark.
| 1 | AC | 0.85 points | 100.0% | 1 | C |
MathVerse-Mini Highlights
The leading models and scores on this benchmark.
What is MathVerse-Mini?
What MathVerse-Mini measures and how its scores work.
MathVerse-Mini is a subset of the MathVerse benchmark for evaluating math reasoning capabilities in vision-language models.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- MathVerse-Mini
- Modality
- image
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mathverse-mini|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MathVerse-Mini.
Which model scores highest on MathVerse-Mini?
Qwen3 VL 235B A22B Thinking is currently ranked first with 0.85 points.
What does MathVerse-Mini measure?
MathVerse-Mini is a subset of the MathVerse benchmark for evaluating math reasoning capabilities in vision-language models.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.