Benchmark
Graphwalks BFS <128k Benchmark
What is Graphwalks BFS <128k?
A graph reasoning benchmark that evaluates language models' ability to perform breadth-first search (BFS) operations on graphs with context length under 128k…
- Modality
- text
- Evaluates
- reasoning, spatial reasoning
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 11
Source provenance
Graphwalks BFS <128k results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-4.1 | OpenAI | 0.617 | 2025-04-14 | evidence |
| GPT-4.1 mini | OpenAI | 0.617 | 2025-04-14 | evidence |
| GPT-4.1 nano | OpenAI | 0.25 | 2025-04-14 | evidence |
| GPT-4.5 | OpenAI | 0.723 | 2025-02-27 | evidence |
| GPT-4o | OpenAI | 0.417 | 2024-08-06 | evidence |
| GPT-5 | OpenAI | 0.783 | 2025-08-07 | evidence |
| GPT-5.2 | OpenAI | 0.94 | 2025-12-11 | evidence |
| GPT-5.4 | OpenAI | 0.93 | 2026-03-05 | evidence |
| GPT-5.4 mini | OpenAI | 0.763 | 2026-03-17 | evidence |
| GPT-5.4 nano | OpenAI | 0.734 | 2026-03-17 | evidence |
| o3-mini | OpenAI | 0.51 | 2025-01-30 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.