math benchmark
MathVision Leaderboard
MathVision is a math benchmark for multimodal mathematical reasoning.
Updated Sep 7, 2026
Models35
Model coverage35
MetricScore
EvidenceB
MathVision Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score97.80% | Percentile100.00% | Participants35 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score95.70% | Percentile97.06% | Participants35 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score95.70% | Percentile94.12% | Participants35 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score94.60% | Percentile91.18% | Participants35 | EvidenceC | Evaluated |
| Rank05 | ModelBY | Score94.50% | Percentile88.24% | Participants35 | EvidenceC | Evaluated |
| Rank06 | ModelMA | Score93.20% | Percentile85.29% | Participants35 | EvidenceC | Evaluated |
| Rank07 | ModelBY | Score92.70% | Percentile82.35% | Participants35 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score90.30% | Percentile79.41% | Participants35 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score88.00% | Percentile76.47% | Participants35 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score86.20% | Percentile73.53% | Participants35 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score86.00% | Percentile70.59% | Participants35 | EvidenceC | Evaluated |
| Rank12 | ModelGO | Score85.60% | Percentile67.65% | Participants35 | EvidenceC | Evaluated |
| Rank13 | ModelMA | Score84.20% | Percentile64.71% | Participants35 | EvidenceC | Evaluated |
| Rank14 | ModelAC | Score83.90% | Percentile61.76% | Participants35 | EvidenceC | Evaluated |
| Rank15 | ModelGO | Score82.40% | Percentile58.82% | Participants35 | EvidenceC | Evaluated |
| Rank16 | ModelGO | Score79.70% | Percentile55.88% | Participants35 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score74.60% | Percentile52.94% | Participants35 | EvidenceC | Evaluated |
| Rank18 | ModelST | Score70.80% | Percentile50.00% | Participants35 | EvidenceC | Evaluated |
| Rank19 | ModelGO | Score70.50% | Percentile47.06% | Participants35 | EvidenceC | Evaluated |
| Rank20 | ModelAC | Score70.20% | Percentile44.12% | Participants35 | EvidenceC | Evaluated |
| Rank21 | ModelAC | Score66.50% | Percentile41.18% | Participants35 | EvidenceC | Evaluated |
| Rank22 | ModelAC | Score65.70% | Percentile38.24% | Participants35 | EvidenceC | Evaluated |
| Rank23 | ModelAC | Score63.40% | Percentile35.29% | Participants35 | EvidenceC | Evaluated |
| Rank24 | ModelAC | Score62.70% | Percentile32.35% | Participants35 | EvidenceC | Evaluated |
| Rank25 | ModelAC | Score60.20% | Percentile29.41% | Participants35 | EvidenceC | Evaluated |
| Rank26 | ModelAC | Score60.00% | Percentile26.47% | Participants35 | EvidenceC | Evaluated |
| Rank27 | ModelGO | Score59.50% | Percentile23.53% | Participants35 | EvidenceC | Evaluated |
| Rank28 | ModelAC | Score53.90% | Percentile20.59% | Participants35 | EvidenceC | Evaluated |
| Rank29 | ModelGO | Score52.40% | Percentile17.65% | Participants35 | EvidenceC | Evaluated |
| Rank30 | ModelAC | Score51.60% | Percentile14.71% | Participants35 | EvidenceC | Evaluated |
MathVision Highlights
The leading models and scores on this benchmark.
MathVision Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MathVision
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MathVision?
What MathVision measures and how its scores work.
MathVision is a dataset designed to measure multimodal mathematical reasoning capabilities.
It measures how well models solve mathematical problems requiring both visual understanding and mathematical reasoning, reported as a Score in ratio units.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MathVision
- 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 MathVision.
Which model scores highest on MathVision?
Kimi K3 is currently ranked first with 97.80%.
What are the top three models on MathVision?
The current leaders are Kimi K3 (97.80%), Qwen3.8-Flash-Next (95.70%), and Qwen3.8 Flash (95.70%).
Which MathVision model has the lowest official input price?
Qwen2.5-Omni-7B has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among MathVision results?
The fastest matched records are Gemma 4 31B (22.86 tok/s via FriendliAI), Qwen3 VL 4B Thinking (8.77 tok/s via DeepInfra), and Kimi K2.6 (1.24 tok/s via Moonshot AI).
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.