Long-context graph traversal benchmark using breadth-first search tasks.
BenchLM mirrors the published score view for Graphwalks BFS 128K. MAI-Thinking-1 leads the public snapshot at 90%. BenchLM does not use these results to rank models overall.
Year
2026
Tasks
Graph traversal tasks
Format
Long-context graph reasoning
Difficulty
Algorithmic long-context reasoning
Graphwalks BFS tests whether a model can preserve algorithmic state while traversing graph structures across long contexts.
Version
Graphwalks BFS 128K 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Long-context graph traversal benchmark using breadth-first search tasks.
MAI-Thinking-1 by Microsoft currently leads with a score of 90% on Graphwalks BFS 128K.
1 AI models have been evaluated on Graphwalks BFS 128K on BenchLM.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.