# Expert-SWE (Internal) — AI model rankings

OpenAI's private set of expert-level software-engineering problems. Higher is better.

2 tracked models have a published Expert-SWE (Internal) 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-5.5 | OpenAI | 73.1% | Lab | Apr 23 2026 |
| 2 | GPT-5.4 | OpenAI | 68.5% | Lab | Mar 5 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/expert-swe
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.