# Graphwalks BFS 128K leaderboard

Reasoning benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/reasoning-graphwalks-bfs128k

Graphwalks BFS 0K-128K. Every model the catalog carries a published Graphwalks BFS 128K value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Reasoning |
| Measure | Long-context graph reasoning |
| Tasks | Graph traversal tasks |
| Difficulty | Algorithmic long-context reasoning |
| Published by | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |

Long-context graph traversal benchmark using breadth-first search tasks.

## Graphwalks BFS 128K ranking

2 models with a published Graphwalks BFS 128K value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Long-context graph reasoning | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Gemini 4 Argon](https://modelchoice.dev/models/gemini-4-argon) | Google | 99.7 | Observed 2026-11-21 · source benchlm:models |
| 2 | [MAI-Thinking-1](https://modelchoice.dev/models/mai-thinking-1) | Microsoft | 90 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
