Inference

MathVision

A visual mathematics benchmark that tests whether a model can solve math problems grounded in diagrams, equations, figures, and other visual inputs.

  • Not in index
  • Multimodal
ModelsModels with a result.19
Top resultBest result on this test.N/A
Top-3 spreadPoints from first to third.N/A
YearYear of release.N/A

Result and price

020406080100$1$3$10$30RESULTOUTPUT PRICE PER 1M TOKENS · LOG SCALE

Results

19 results
#ModelResultThe score from the source.
—Qwen3.8 Max95.2%
—Kimi K394.3%
—Seed 2.1 Pro92.6%
—Qwen3.8-Omni-Flash91.8%
—Qwen3.8-Flash-Next90.6%
—Qwen3.7 Plus90.3%
—Seed 2.1 Turbo90.1%
—Qwen3.8-27B90.0%
—Qwen3.5 397B88.6%
—Qwen3.6 Plus88.0%
—dots3-note Preview87.7%
—Kimi K2.687.4%
—Gemini 3 Pro86.6%
—Qwen3.5-122B-A10B86.2%
—Qwen3.5-27B86.0%
—Qwen3.5-35B-A3B83.9%
—GPT-5.283.0%
—Gemma 4 12B79.7%
—Claude Opus 4.574.3%