math benchmark
DynaMath Leaderboard
DynaMath is a multimodal mathematics and reasoning benchmark focused on dynamic visual problem solving.
Updated Sep 5, 2026
Models7
Model coverage7
MetricScore
EvidenceB
DynaMath Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score88.00% | Percentile100.00% | Participants7 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score87.70% | Percentile83.33% | Participants7 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score85.90% | Percentile66.67% | Participants7 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score85.60% | Percentile50.00% | Participants7 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score85.00% | Percentile33.33% | Participants7 | EvidenceC | Evaluated |
| Rank06 | ModelBY | Score73.10% | Percentile16.67% | Participants7 | EvidenceC | Evaluated |
| Rank07 | ModelBY | Score68.10% | Percentile0.00% | Participants7 | EvidenceC | Evaluated |
DynaMath Highlights
The leading models and scores on this benchmark.
DynaMath Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for DynaMath
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is DynaMath?
What DynaMath measures and how its scores work.
DynaMath is a benchmark for multimodal mathematics and reasoning with dynamic visual problem solving.
It measures performance on dynamic visual mathematics and reasoning problems using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- DynaMath
- 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 DynaMath.
Which model scores highest on DynaMath?
Qwen3.6 Plus is currently ranked first with 88.00%.
What are the top three models on DynaMath?
The current leaders are Qwen3.6 Plus (88.00%), Qwen3.5-27B (87.70%), and Qwen3.5-122B-A10B (85.90%).
Which DynaMath model has the lowest official input price?
Qwen3.5-35B-A3B has the lowest matched official input price at $0.25 input / $2.0 output per 1M tokens.
Which models are fastest among DynaMath 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.