math benchmark
MathVista-Mini Leaderboard
MathVista-Mini is a smaller version of the MathVista benchmark for evaluating mathematical reasoning in visual contexts.
Updated Sep 5, 2026
Models25
Model coverage25
MetricScore
EvidenceB
MathVista-Mini Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score90.10% | Percentile100.00% | Participants25 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score87.80% | Percentile95.83% | Participants25 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score87.40% | Percentile91.67% | Participants25 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score87.40% | Percentile87.50% | Participants25 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score86.40% | Percentile83.33% | Participants25 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score86.20% | Percentile79.17% | Participants25 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score85.90% | Percentile75.00% | Participants25 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score85.80% | Percentile70.83% | Participants25 | EvidenceC | Evaluated |
| Rank09 | ModelLA | Score85.00% | Percentile66.67% | Participants25 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score84.90% | Percentile62.50% | Participants25 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score83.80% | Percentile58.33% | Participants25 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score81.90% | Percentile54.17% | Participants25 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score81.40% | Percentile50.00% | Participants25 | EvidenceC | Evaluated |
| Rank14 | ModelAC | Score80.10% | Percentile45.83% | Participants25 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score79.50% | Percentile41.67% | Participants25 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score77.20% | Percentile37.50% | Participants25 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score74.80% | Percentile33.33% | Participants25 | EvidenceC | Evaluated |
| Rank18 | ModelAC | Score74.70% | Percentile29.17% | Participants25 | EvidenceC | Evaluated |
| Rank19 | ModelAC | Score73.70% | Percentile25.00% | Participants25 | EvidenceC | Evaluated |
| Rank20 | ModelAC | Score70.50% | Percentile20.83% | Participants25 | EvidenceC | Evaluated |
| Rank21 | ModelLA | Score68.50% | Percentile16.67% | Participants25 | EvidenceC | Evaluated |
| Rank22 | ModelAC | Score68.20% | Percentile12.50% | Participants25 | EvidenceC | Evaluated |
| Rank23 | ModelGO | Score67.60% | Percentile8.33% | Participants25 | EvidenceC | Evaluated |
| Rank24 | ModelGO | Score62.90% | Percentile4.17% | Participants25 | EvidenceC | Evaluated |
| Rank25 | ModelGO | Score50.00% | Percentile0.00% | Participants25 | EvidenceC | Evaluated |
MathVista-Mini Highlights
The leading models and scores on this benchmark.
MathVista-Mini Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MathVista-Mini
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MathVista-Mini?
What MathVista-Mini measures and how its scores work.
MathVista-Mini consists of examples derived from multimodal datasets involving mathematics and combines diverse mathematical and visual tasks.
It measures the ability to solve problems requiring both visual understanding and mathematical reasoning, reported as a Score ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MathVista-Mini
- 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 MathVista-Mini.
Which model scores highest on MathVista-Mini?
Kimi K2.5 is currently ranked first with 90.10%.
What are the top three models on MathVista-Mini?
The current leaders are Kimi K2.5 (90.10%), Qwen3.5-27B (87.80%), and Qwen3.5-122B-A10B (87.40%).
Which MathVista-Mini model has the lowest official input price?
Qwen3.6-35B-A3B has the lowest matched official input price at $0.25 input / $1.5 output per 1M tokens.
Which models are fastest among MathVista-Mini results?
The fastest matched records are Gemma 3 27B (33.00 tok/s via DeepInfra), Gemma 3 12B (33.00 tok/s via DeepInfra), and Gemma 3 4B (33.00 tok/s via DeepInfra).
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.