89 curated builds·evidence labeled
OFFICIAL

Wikiracing Fast Navigation

An official benchmark demonstrating Jev selecting optimal Wikipedia links in real time to reach target concepts.

Overview & Result

In the classic Wikiracing challenge (navigating between two unrelated Wikipedia articles using only internal links), Jev acts as the real-time choice model, evaluating candidate links and advancing hops in tens of milliseconds rather than waiting seconds per generative step.

How Jev fits in the loop

  1. Extract all viable article links from the current Wikipedia DOM.
  2. Format the target topic and candidate link list as a typed Choice schema.
  3. Jev evaluates semantic proximity and outputs the highest probability link.
  4. Playwright navigates to the next page and checks termination criteria.

How to reproduce

  1. Fetch the candidate links on the current Wikipedia article using the MediaWiki API or DOM parser.
  2. Pass the target concept and the link candidate array into a bounded Jev Choice call.
  3. Execute the chosen transition in Playwright or browser session until the target page is reached.

Why this build matters

Proves that in high-cardinality action spaces where choices are discrete and bounded, a System 1 classifier outpaces generative models by orders of magnitude in speed and cost.

Reported performance

Reported by author

Latency: <50ms per link selection hop

Recorded in the vendor's official Wikiracing demonstration comparing Jev's fast step decisions against traditional multi-second generative LLM latency.

Limitations

  • This benchmark was conducted by the vendor on Wikipedia structured linking.
  • Real-world web navigation frequently encounters dynamic SPAs, popups, and anti-bot challenges that require broader fallback logic.
  • Does not invent new search keywords or synthesis outside the provided link set.

Patterns