Graphwalks Parents 256k F1: leaderboard
Graphwalks parent-node long-context reasoning task reported at 256k context with F1 scoring.
Metric: F1 (system card). Source: openai.com. Source: benchmarklist.com. Saturation forecast: Around October 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos 5 | 99.96 | #2 |
| 2 | Claude Mythos Preview | 99.9 | #4 |
| 3 | Claude Opus 4.8 | 99.3 | #37 |
| 4 | Claude Opus 4.6 | 95.4 | #63 |
| 5 | Claude Opus 4.7 | 93.6 | #49 |
| 6 | GPT-5.5 | 90.1 | #31 |
| 7 | GPT-5.4 | 82.8 | #79 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=graphwalks-parents-256k-f1 · How It Works · Data refreshed daily, snapshot 2026-10-20.