GraphWalks

Measures: The prompt holds a directed graph as a long edge list (up to about 1M tokens); the model must return the nodes reached by a breadth-first search at a given depth, or a node's parents; scored by F1 against the true node set.

Maintainer: OpenAI
Introduced: 2025
Status: Active
Saturation: Headroom
Typical provenance: Self-reported
In scoring set: No

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.