Graphwalks BFS 256k F1: leaderboard
Graphwalks breadth-first-search long-context reasoning task reported at 256k context with F1 scoring.
Metric: F1 (mixed sources). Source: openai.com. Source: benchmarklist.com. Saturation forecast: Around November 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 95.4 | #19 |
| 2 | GPT-5.6 Terra | 94.9 | #41 |
| 3 | GPT-5.6 Luna | 92.5 | #68 |
| 4 | Claude Mythos 5 | 91.1 | #2 |
| 5 | GPT-5.5 | 88.1 | #31 |
| 6 | Claude Opus 4.8 | 85.9 | #37 |
| 7 | Claude Mythos Preview | 85.7 | #4 |
| 8 | Claude Opus 4.7 | 76.9 | #49 |
| 9 | GPT-5.4 | 62.5 | #79 |
| 10 | Claude Opus 4.6 | 61.1 | #63 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=graphwalks-bfs-256k-f1 · How It Works · Data refreshed daily, snapshot 2026-10-20.