Graphwalks BFS >128k
A graph reasoning benchmark that evaluates language models' ability to perform breadth-first search (BFS) operations on graphs with context length over 128k tokens, testing long-context reasoning capabilities.
7rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score, Normalized Score
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Claude Mythos Preview | 0.80 |  Claude Mythos Preview anthropic-claude-mythos-preview | Self-reported | 2026-05-06 |
| 2 | Claude Opus 4.6 | 0.61 | Claude Opus 4.6 anthropic-claude-opus-4.6 | Self-reported | 2026-05-06 |
| 3 | GPT-5.5 | 0.45 |  GPT-5.5 openai-gpt-5.5 | Self-reported | 2026-05-06 |
| 4 | GPT-5.4 | 0.21 | GPT-5.4 openai-gpt-5.4 | Self-reported | 2026-05-06 |
| 5 | GPT-4.1 | 0.19 | GPT-4.1 openai-gpt-4.1 | Self-reported | 2026-05-06 |
| 6 | GPT-4.1 mini | 0.15 | GPT-4.1 Mini openai-gpt-4.1-mini | Self-reported | 2026-05-06 |
| 7 | GPT-4.1 nano | 0.03 | GPT-4.1 Nano openai-gpt-4.1-nano | Self-reported | 2026-05-06 |
No matching rows.