# GraphWalks BFS 256K–1M 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://modelscale.dev/leaderboards/benchmarks/reasoning-graphwalks-bfs256k1m

Every model the catalog carries a published GraphWalks BFS 256K–1M value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Reasoning |
| Measure | F1 |
| Tasks | Breadth-first-search graph traversal on 200 problems with context lengths from 256K to 1M tokens. |
| Difficulty | Frontier agent evaluation |
| Published by | [Gemini 4 Argon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-argon) |

Breadth-first-search graph traversal on 200 problems with context lengths from 256K to 1M tokens.

## GraphWalks BFS 256K–1M ranking

4 models with a published GraphWalks BFS 256K–1M 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 | F1 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 84.2 | Observed 2026-10-23 · source benchlm:models |
| 2 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 71.8 | Observed 2026-10-23 · source benchlm:models |
| 3 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 66.8 | Observed 2026-10-23 · source benchlm:models |
| 4 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 65.0 | Observed 2026-10-23 · 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.