long context benchmark
GraphWalks Leaderboard
GraphWalks is a synthetic multi-hop long-context reasoning benchmark that requires traversing an edge-list graph to find neighboring or parent nodes.
Updated Sep 5, 2026
Models3
Model coverage3
MetricScore
EvidenceB
GraphWalks Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score90.00% | Percentile100.00% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelXI | Score87.00% | Percentile50.00% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelXI | Score62.00% | Percentile0.00% | Participants3 | EvidenceC | Evaluated |
GraphWalks Highlights
The leading models and scores on this benchmark.
GraphWalks Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for GraphWalks
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is GraphWalks?
What GraphWalks measures and how its scores work.
GraphWalks gives a model an edge-list representation of a graph and a start node, requiring it to find neighboring nodes via breadth-first search or parent nodes.
Performance is reported as Score, the F1 of the model-predicted answer set versus the ground truth, with unit ratio.
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
- No
- Evaluation key
- overall
LLM Stats. 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 90.00%.
What are the top three models on GraphWalks?
The current leaders are MAI-Thinking-1 (90.00%), MiMo-V2.5 (87.00%), and MiMo-V2.5-Pro (62.00%).
Which GraphWalks model has the lowest official input price?
MiMo-V2.5 has the lowest matched official input price at $0.14 input / $0.28 output per 1M tokens.
Which models are fastest among GraphWalks results?
The fastest matched records are MiMo-V2.5 (5.39 tok/s via DeepInfra) and MiMo-V2.5-Pro (5.27 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.