reasoning 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 length under 128k tokens.
Updated Sep 5, 2026
Models11
Model coverage11
MetricScore
EvidenceB
Graphwalks BFS <128k Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score94.00% | Percentile100.00% | Participants11 | EvidenceC | Evaluated |
| Rank02 | ModelOP | Score93.00% | Percentile90.00% | Participants11 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score78.30% | Percentile80.00% | Participants11 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score76.30% | Percentile70.00% | Participants11 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score73.40% | Percentile60.00% | Participants11 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score72.30% | Percentile50.00% | Participants11 | EvidenceC | Evaluated |
| Rank07 | ModelOP | Score61.70% | Percentile40.00% | Participants11 | EvidenceC | Evaluated |
| Rank08 | ModelOP | Score61.70% | Percentile30.00% | Participants11 | EvidenceC | Evaluated |
| Rank09 | ModelOP | Score51.00% | Percentile20.00% | Participants11 | EvidenceC | Evaluated |
| Rank10 | ModelOP | Score41.70% | Percentile10.00% | Participants11 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score25.00% | Percentile0.00% | Participants11 | 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 graph reasoning benchmark in which language models perform breadth-first search (BFS) operations on graphs and return nodes reachable at specified depths.
It measures the Score, expressed as a ratio, for returning nodes reachable at specified depths in graphs with context length under 128k tokens.
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
- reasoning
- 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-5.2 is currently ranked first with 94.00%.
What are the top three models on Graphwalks BFS <128k?
The current leaders are GPT-5.2 (94.00%), GPT-5.4 (93.00%), and GPT-5 (78.30%).
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-4.1 mini (467.39 tok/s via OpenAI), GPT-4.1 nano (138.14 tok/s via OpenAI), and GPT-4o (132.00 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.