Benchmark profile

Graphwalks parents 0-128K (Graphwalks Parents 128K)

Long-context benchmark for recovering parent relationships inside graph tasks.

Data verified July 23, 2026

How BenchLM shows Graphwalks Parents 128K right now

BenchLM is tracking Graphwalks Parents 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.

4 tracked modelsLocal tracked rowsAwaiting exact-source attachmentsDisplay only

Introducing GPT-5.4 mini and nano

Tracked score on Graphwalks Parents 128K — July 23, 2026

BenchLM mirrors the published tracked score view for Graphwalks Parents 128K. GPT-5.4 leads the public snapshot at 89.8% , followed by GPT-5.4 mini (71.5%) and GPT-5 mini (64.3%). BenchLM does not use these results to rank models overall.

GPT-5.4

OpenAI

gpt-5-4

89.8%

Overall —

GPT-5.4 mini

OpenAI

gpt-5-4-mini

71.5%

Overall —

GPT-5 mini

OpenAI

gpt-5-mini

64.3%

Overall —

4 modelsReasoningCurrentDisplay onlyUpdated July 23, 2026

Tracked score table (4 models)

Score

GPT-5.4OpenAI

89.8%

GPT-5.4 miniOpenAI

71.5%

GPT-5 miniOpenAI

64.3%

GPT-5.4 nanoOpenAI

50.8%

The published Graphwalks Parents 128K snapshot places GPT-5.4 first at 89.8%. The third row is 25.5 points behind. The broader top-10 range is 39.0 points, so the table still separates the published systems.

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

About Graphwalks Parents 128K

Year

2026

Tasks

Graph parent-retrieval tasks

Format

Long-context graph reasoning

Difficulty

Algorithmic long-context reasoning

Measures whether models can keep structural relationships straight across long contexts.

Introducing GPT-5.4 mini and nano Public benchmark source

BenchLM freshness & provenance

Version

Graphwalks Parents 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.

FAQ

What does Graphwalks Parents 128K measure?

Long-context benchmark for recovering parent relationships inside graph tasks.

Which model leads the published Graphwalks Parents 128K snapshot?

GPT-5.4 currently leads the published Graphwalks Parents 128K snapshot with 89.8% tracked score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Graphwalks Parents 128K?

4 AI models are included in BenchLM's mirrored Graphwalks Parents 128K snapshot, based on the public leaderboard captured on July 23, 2026.

Last updated: July 23, 2026 · mirrored from the public benchmark leaderboard

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.