long context benchmark
Graphwalks BFS >128k Leaderboard
Graphwalks BFS >128k is a graph reasoning benchmark for evaluating language models on breadth-first search (BFS) operations over graphs with context lengths exceeding 128k tokens.
Updated Oct 23, 2026
Models12
Model coverage12
MetricScore
EvidenceB
Graphwalks BFS >128k Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score90.70% | Percentile100.00% | Participants12 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score84.20% | Percentile90.91% | Participants12 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score81.30% | Percentile81.82% | Participants12 | EvidenceC | Evaluated |
| Rank04 | ModelAN | Score80.00% | Percentile72.73% | Participants12 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score76.90% | Percentile63.64% | Participants12 | EvidenceC | Evaluated |
| Rank06 | ModelAN | Score68.10% | Percentile54.55% | Participants12 | EvidenceC | Evaluated |
| Rank07 | ModelAN | Score61.50% | Percentile45.45% | Participants12 | EvidenceC | Evaluated |
| Rank08 | ModelOP | Score45.40% | Percentile36.36% | Participants12 | EvidenceC | Evaluated |
| Rank09 | ModelOP | Score21.40% | Percentile27.27% | Participants12 | EvidenceC | Evaluated |
| Rank10 | ModelOP | Score19.00% | Percentile18.18% | Participants12 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score15.00% | Percentile9.09% | Participants12 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score2.90% | Percentile0.00% | Participants12 | EvidenceC | Evaluated |
Graphwalks BFS >128k Highlights
The leading models and scores on this benchmark.
Graphwalks BFS >128k Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Graphwalks BFS >128k
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Graphwalks BFS >128k?
What Graphwalks BFS >128k measures and how its scores work.
A long-context graph reasoning benchmark focused on breadth-first search (BFS) operations.
It measures language models' ability to perform BFS on graphs with context lengths over 128k tokens, using Score as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Graphwalks BFS >128k
- 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 BFS >128k.
Which model scores highest on Graphwalks BFS >128k?
GPT-5.6 Sol is currently ranked first with 90.70%.
What are the top three models on Graphwalks BFS >128k?
The current leaders are GPT-5.6 Sol (90.70%), Gemini 4 Argon (84.20%), and GPT-5.6 Luna (81.30%).
Which Graphwalks BFS >128k model has the lowest official input price?
GPT-4.1 nano has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among Graphwalks BFS >128k results?
The fastest matched records are GPT-5.6 Luna (215.52 tok/s via OpenAI), GPT-4.1 nano (200.00 tok/s via OpenAI), and GPT-4.1 mini (150.00 tok/s via OpenAI).
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.