Introducing SWE-bench Verified

We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues.

Updated February 24, 2025

As part of our Preparedness Framework⁠, OpenAI develops a range of metrics to track, evaluate, and forecast models’ abilities to act autonomously. The ability to autonomously complete software engineering tasks is a key component of our Medium risk level in the Model Autonomy risk category. Evaluating these capabilities is challenging due to the complexity of software engineering tasks, the difficulty of accurately assessing generated code, and the challenge of simulating real-world development scenarios. Therefore, our approach to Preparedness must also involve careful examination of evaluations themselves, to reduce the potential for underestimating or overestimating performance in important risk categories.

One of the most popular evaluation suites for software engineering is SWE-bench⁠(opens in a new window)¹—a benchmark for evaluating large language models’ (LLMs’) abilities to solve real-world software issues sourced from GitHub. The benchmark involves giving agents a code repository and issue description, and challenging them to generate a patch that resolves the problem described by the issue. Coding agents have made impressive progress on SWE-bench, with top scoring agents scoring 20% on SWE-bench and 43% on SWE-bench Lite according to the SWE-bench leaderboard⁠(opens in a new window) as of August 5, 2024.

Our testing identified some SWE-bench tasks which may be hard or impossible to solve, leading to SWE-bench systematically underestimating models’ autonomous software engineering capabilities. We’ve collaborated with the authors of SWE-bench to address those issues in a new release of the benchmark that should provide more accurate evaluations.

Background on SWE-bench

Adapting SWE-bench as a Preparedness Evaluation

Here is an example illustrating the first of these issues.