# SWE-Atlas Refactoring leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/agentic-swe-atlas-refactoring

Every model the catalog carries a published SWE-Atlas Refactoring value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Refactoring score with confidence intervals |
| Tasks | SWE-Atlas refactoring tasks |
| Difficulty | Real-world software-engineering agent tasks |
| Published by | [SWE-Atlas](https://labs.scale.com/papers/sweatlas) |

A Scale SWE-Atlas software-engineering agent benchmark focused on refactoring tasks.

## SWE-Atlas Refactoring ranking

No model in the catalog has a published SWE-Atlas Refactoring score. The benchmark is defined by SWE-Atlas, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
