long context benchmark
GraphWalks
GraphWalks is a synthetic multi-hop long-context reasoning benchmark in which a model is given an edge-list representation of a graph and must traverse it to find neighboring nodes (via breadth-first search) or parent nodes for a given start node. Performance is reported as F1 of the model-predicted answer set versus the ground truth.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
GraphWalks Ranking
Higher score ranks better on this benchmark.
| 1 | MI | 90.0% | 100.0% | 3 | C | |
| 2 | XI | 87.0% | 50.0% | 3 | C | |
| 3 | XI | 62.0% | 0.0% | 3 | C |
GraphWalks Score Distribution
A closer view of the leading scores on this benchmark.
GraphWalks Highlights
The leading models and scores on this benchmark.
What is GraphWalks?
What GraphWalks measures and how its scores work.
GraphWalks is a synthetic multi-hop long-context reasoning benchmark in which a model is given an edge-list representation of a graph and must traverse it to find neighboring nodes (via breadth-first search) or parent nodes for a given start node. Performance is reported as F1 of the model-predicted answer set versus the ground truth.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- GraphWalks
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- graphwalks|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about GraphWalks.
Which model scores highest on GraphWalks?
MAI-Thinking-1 is currently ranked first with 90.0%.
What does GraphWalks measure?
GraphWalks is a synthetic multi-hop long-context reasoning benchmark in which a model is given an edge-list representation of a graph and must traverse it to find neighboring nodes (via breadth-first search) or parent nodes for a given start node. Performance is reported as F1 of the model-predicted answer set versus the ground truth.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.