Talk about your next project
doubleAI content marketing

The lesson

Introduce a benchmark by naming the gap first, then show its construction, sample tasks and scoring rules before sending readers to the full paper.

The move

The article opens with the title, a one-line claim about a reasoning benchmark, metadata, contents and related research links. A “TL;DR” summarizes FormulaOne as “220 novel dynamic programming problems over graphs” in three tiers, then points to the full paper. The body explains why doubleAI built the benchmark, shows a tier table for Shallow, Deeper and Deepest, gives example problems from each tier, then explains Courcelle’s theorem, tree decompositions and the evaluation checks: Correctness, Consistency and Efficiency.

Why it works

  • Our readThe TL;DR gives technical readers the whole claim before they commit to the longer explanation.
  • Our readThe tier table and named example problems make the benchmark feel concrete instead of only theoretical.
  • Our readThe evaluation criteria state how submissions are judged, which helps readers trust that the benchmark is more than a collection of hard prompts.

What not to copy

Don't copy FormulaOne, the graph-theory framing or doubleAI's benchmark claims. Keep the structure of gap, benchmark design, sample tasks, theory explanation and evaluation rules.

More content marketing

Steal it for your brand.

Tell us what you want to make. We’ll talk through how to put these ideas to work for your brand.