DynaMath

A multimodal benchmark for dynamic mathematical reasoning over visual and structured inputs.

ModelsModels with a result.7
Top resultBest result on this benchmark.—
Top-3 spreadPoints from first to third.—
YearYear of release.—

Result and price

6 of 7 results

Results

7 results
#ModelResultThe score from the source.
—GPT-5.286.8%
—Qwen3.5 397B86.3%
—Qwen3.6-27B85.6%
—Gemini 3 Pro85.1%
—Kimi K2.584.4%
—LFM3-VL-2B79.2%