aiaimodel.cards
← All benchmarks

AutomationBench (Public)

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

  1. 1DeepSeek-V4-Pro · DeepSeek
    31.8%

How each maker reported it

  • DeepSeek-V4-Pro model card (0813)

    Code-agent tasks use DeepSeek Harness minimal mode at max effort, temperature 1.0, top_p 0.95. DSBench rows are DeepSeek internal test sets. Competitor figures as published by DeepSeek.

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