Graphwalks BFS 256k F1: leaderboard
Graphwalks breadth-first-search long-context reasoning task reported at 256k context with F1 scoring.
Metric: F1 (self-reported). Source: benchmarklist.com. Status: years away from saturation. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 95.4 |
| 2 | GPT-5.6 Terra | 94.9 |
| 3 | GPT-5.6 Luna | 92.5 |
| 4 | Claude Mythos 5 | 91.1 |
| 5 | GPT-5.5 | 88.1 |
| 6 | Claude Opus 4.8 | 85.9 |
| 7 | Claude Mythos Preview | 85.7 |
| 8 | Claude Opus 4.7 | 76.9 |
| 9 | GPT-5.4 | 62.5 |
| 10 | Claude Opus 4.6 | 61.1 |
Interactive version: theaggregate.ai/benchmark?slug=graphwalks-bfs-256k-f1 · How It Works · Data refreshed daily, snapshot 2026-09-05.