Updated daily at 05:00 UTC
Benchmark
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
Independent and third-party results only.
No independent or third-party results yet. Show all results