benchmarks evals
The Models Could Navigate the Encyclopedia. Humans Still Held Up.
A link-following game tests retrieval across five Wikipedia languages and five literature datasets.
Summary
A link-following game tests retrieval across five Wikipedia languages and five literature datasets.
The Wikipedia Game requires reaching a target article using only links from the current page. Researchers used local Wikipedia and academic-citation graphs to compare language models, embedding methods, people and TF-IDF baselines without relying on third-party navigation APIs. No model significantly outperformed humans, although the best evaluated models achieved comparable success. Rankings changed across languages and subject areas. The authors provide graph-building and navigation code, making the test a reproducible way to examine information-finding skills rather than another open-ended chat demonstration.
Why it matters
A link-following game tests retrieval across five Wikipedia languages and five literature datasets.
Limits and context
- The Wikipedia Game requires reaching a target article using only links from the current page.
Key claims
A link-following game tests retrieval across five Wikipedia languages and five literature datasets.
Qualification: The Wikipedia Game requires reaching a target article using only links from the current page.
Evidence: source-2026-10-12-011
Sources
- arXiv preprint 2610.13948, original v1arXiv / submitting research authors · primary research
Corrections
: Publication note: The October 12, 2026 edition was prepared and published late on October 12 after the scheduled newsroom task could not start. The edition retains its October 12 date and 9:00 AM America/Detroit reveal time. Reports use sources available before that cutoff; actual preparation and image-generation times are preserved in the provenance records.