# SWE-Marathon leaderboard

external 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://modelscale.dev/leaderboards/benchmarks/external-swe-marathon

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

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Task resolution and trajectory review |
| Tasks | 20 multi-hour software engineering tasks |
| Difficulty | Ultra-long-horizon software engineering |
| Published by | [SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?](https://www.swe-marathon.org/) |

A long-horizon software engineering benchmark from Abundant AI with multi-hour tasks spanning library reproductions, full-stack product clones, and ML engineering.

## SWE-Marathon ranking

No model in the catalog has a published SWE-Marathon score. The benchmark is defined by SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?, 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.
