# GraphWalks BFS (<128K) — AI model rankings

breadth-first traversal accuracy for inputs shorter than 128K tokens

10 tracked models have a published GraphWalks BFS (<128K) score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | GPT-5.2 | OpenAI | 94% | Lab | Dec 11 2025 |
| 2 | GPT-5.4 | OpenAI | 93% | Lab | Mar 5 2026 |
| 3 | GPT-5 | OpenAI | 78.3% | Lab | Aug 7 2025 |
| 4 | GPT-5.4 mini | OpenAI | 76.3% | Lab | Mar 17 2026 |
| 5 | GPT-5 mini | OpenAI | 73.4% | Lab | Aug 7 2025 |
| 5 | GPT-5.4 nano | OpenAI | 73.4% | Lab | Mar 17 2026 |
| 7 | GPT-5 nano | OpenAI | 64% | Lab | Aug 7 2025 |
| 8 | GPT-4.1 | OpenAI | 61.7% | Lab | Apr 14 2025 |
| 8 | GPT-4.1 mini | OpenAI | 61.7% | Lab | Apr 14 2025 |
| 10 | GPT-4.1 nano | OpenAI | 25% | Lab | Apr 14 2025 |


---

Canonical page: https://aireleasetracker.com/benchmark/graphwalks-bfs-under-128k
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.