aiaimodel.cards
← All benchmarks

MMMU Pro

College-level questions that require reading images, charts and diagrams.

  1. 1Gemini 3.1 Pro · Google
    80.5%
  2. 2Gemma 4 31B · Google
    76.9%
  3. 3Muse Glimmer 30B · Meta
    74.0%

How each maker reported it

  • Gemini 3.1 Pro p.4

    Results as of February 2026, Gemini at Thinking (High); competitors at their highest reported settings, as listed by Google.

  • Gemma 4 31B Benchmark results

    Instruction-tuned models, as published in Google's model card. OmniDocBench is edit distance (lower is better). Audio benchmarks are omitted because 31B has no audio input.

  • Muse Glimmer 30B Benchmarks

    Meta's own results. Muse Glimmer at high reasoning; Gemma4-31B and Qwen3.6-27B in thinking mode. GDPVal-AA v2 is an Elo-style score.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.