DynaMath
We show this table for reference; we do not rank on it.
A multimodal benchmark for dynamic mathematical reasoning over visual and structured inputs.
Benchmark score on DynaMath — September 27, 2026
We compile the DynaMath rows from provider self-reports. Qwen3.6-27B leads the table at 85.6%. We do not use these results to rank models overall.
1 modelMultimodal & GroundedCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (1 model)
ScoreAbout DynaMath
Year
2026
Tasks
Dynamic visual math problems
Format
Multimodal mathematical reasoning
Difficulty
Advanced multimodal mathematics
DynaMath is intended to probe whether models can track changing mathematical structure in multimodal settings rather than solving static text-only equations.
Freshness and provenance
Version
DynaMath 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does DynaMath measure?
A multimodal benchmark for dynamic mathematical reasoning over visual and structured inputs.
Which model scores highest on DynaMath?
Qwen3.6-27B by Alibaba currently leads with a score of 85.6% on DynaMath.
How many models are evaluated on DynaMath?
1 AI models have been evaluated on DynaMath on BenchLM.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.