aiaimodel.cards
← All benchmarks

MRCR v2 8-needle 128K (average)

We haven't written a description for this benchmark yet; see the card notes below for how each maker ran it.

  1. 1Gemini 3.1 Pro · Google
    84.9%
  2. 2Gemma 4 31B · Google
    66.4%

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.

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