Graphwalks Parents 256k F1 — leaderboard

Graphwalks parent-node long-context reasoning task reported at 256k context with F1 scoring.

Metric: F1 (self-reported). Source: benchmarklist.com. Status: saturation imminent. 7 models tracked.

Top models

#ModelScore
1Claude Mythos 599.96
2Claude Mythos Preview99.9
3Claude Opus 4.899.3
4Claude Opus 4.695.4
5Claude Opus 4.793.6
6GPT-5.590.1
7GPT-5.482.8

Interactive version: theaggregate.ai/benchmark?slug=graphwalks-parents-256k-f1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.