DynaMath

math

A multimodal mathematics and reasoning benchmark focused on dynamic visual problem solving.

Methodology

Imported from llm-stats public benchmark metadata. Modality: multimodal. Max score: 1. Categories: math, multimodal, reasoning, vision. Language: en. Verified by llm-stats: no.

Leaderboard

  1. Qwen3.6 Plus self-reported llm-stats
    88.0%
  2. Qwen3.5-27B self-reported llm-stats
    87.7%
  3. Qwen3.5-122B-A10B self-reported llm-stats
    85.9%
  4. Qwen3.6-27B self-reported llm-stats
    85.6%
  5. Qwen3.5-35B-A3B self-reported llm-stats
    85.0%