aiaimodel.cards
← All benchmarks

SWE-Bench Pro (Public)

Fixing real issues in real open-source repositories; a patch counts only if the project's own tests pass. Variants differ in task set and languages.

  1. 1Gemini 3.5 Flash-Lite · Google
    54.2%
  2. 2Gemini 3.1 Pro · Google
    54.2%

How each maker reported it

  • Gemini 3.5 Flash-Lite p.4

    Results as of July 2026, as published in Google's model card. Competitor figures are as listed by Google.

  • 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.

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