GraphWalks — Parents task, 1M-token context subset — Distinct task (Parents vs BFS) and subset (1M) from all other GraphWalks.
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Claude Mythos 5 | Anthropic | 95.5 | 1 | 2026-06-12 |
| 2 | Claude Opus 4.8 | Anthropic | 83.3 | 1 | 2026-06-12 |
| 3 | GPT-5.5 | OpenAI | 58.5 | 1 | 2026-06-12 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.