Skip to main content

Graphwalks BFS 0K-128K (Graphwalks BFS 128K)

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

How BenchLM shows Graphwalks BFS 128K right now

BenchLM is tracking Graphwalks BFS 128K in the local dataset, but exact-source verification records for these rows are still being attached. To avoid a blank benchmark page, BenchLM shows the current tracked rows below as a display-only reference table.

These tracked rows are useful for inspection and spot-checking, but until exact-source attachments are completed they should not be treated as fully verified public benchmark rows.

5 tracked modelsLocal tracked rowsAwaiting exact-source attachmentsDisplay only

Tracked score on Graphwalks BFS 128K — May 1, 2026

BenchLM mirrors the published tracked score view for Graphwalks BFS 128K. GPT-5.4 leads the public snapshot at 93.1% , followed by Claude Mythos Preview (80%) and GPT-5.4 mini (76.3%). BenchLM does not use these results to rank models overall.

5 modelsReasoningCurrentDisplay onlyUpdated May 1, 2026

The published Graphwalks BFS 128K snapshot is tightly clustered at the top: GPT-5.4 sits at 93.1%, while the third row is only 16.8 points behind. The broader top-10 spread is 19.7 points, so the benchmark still separates strong models even when the leaders cluster.

5 models have been evaluated on Graphwalks BFS 128K. The benchmark falls in the Reasoning category. This category carries a 17% weight in BenchLM.ai's overall scoring system. Graphwalks BFS 128K is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Graphwalks BFS 128K

Year

2026

Tasks

Graph traversal tasks

Format

Long-context graph reasoning

Difficulty

Algorithmic long-context reasoning

Graphwalks BFS tests whether a model can preserve algorithmic state while traversing graph structures across long contexts.

BenchLM freshness & provenance

Version

Graphwalks BFS 128K 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Tracked score table (5 models)

1
GPT-5.4gpt-5-4
93.1%
2
Claude Mythos Previewclaude-mythos-preview
80%
3
GPT-5.4 minigpt-5-4-mini
76.3%
4
GPT-5.4 nanogpt-5-4-nano
73.4%
5
GPT-5 minigpt-5-mini
73.4%

FAQ

What does Graphwalks BFS 128K measure?

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

Which model leads the published Graphwalks BFS 128K snapshot?

GPT-5.4 currently leads the published Graphwalks BFS 128K snapshot with a tracked score of 93.1%. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Graphwalks BFS 128K?

5 AI models are included in BenchLM's mirrored Graphwalks BFS 128K snapshot, based on the public leaderboard captured on May 1, 2026.

Last updated: May 1, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.