SWE-EVO

Coding agents implement release-note changes in seven mature Python projects, editing about 21 files per task. Large test suites check each of the 48 tasks.

The paper reports GPT-5.4 with OpenHands at 25%. The arXiv record reached version 6.

In the authors’ words

Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or adding a small feature. However, real-world software engineering is a long-horizon endeavor: developers interpret high-level requirements, coordinate changes across many files, and evolve codebases over multiple iterations while preserving functionality. We introduce SWE-EVO, a benchmark for this long-horizon software evolution challenge. Constructed from release notes of seven mature open-source Python projects, SWE-EVO comprises 48 tasks requiring multi-step modifications spanning an average of 21 files, validated against test suites averaging 874 tests per instance. Experiments reveal a striking capability gap: GPT-5.4 with OpenHands achieves only 25% on SWE-EVO versus 72.80% achieved by GPT-5.2 on SWE-Bench Verified, showing that current agents struggle with sustained, multi-file reasoning. We also propose Fix Rate, a metric capturing partial progress on these complex, long-horizon tasks.

Abstract of SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios (arXiv:2512.18470, CC0)

Made by Le , Thai et al. Released Dec 2025 Fixing real repositories Last in a launch post Feb 2026 , dropped before it saturated Last model added Feb 2026

Level: Expert Specialists with years of training, often over hours of work
Scored: Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers: Agent task Many steps in a terminal, browser, desktop, app, game or robot.

Paper

Model scored in lab cards

Launch post lists it, from 1 lab

System card reports it, from 1 lab

Seed2.0 Pro leads with 8.50%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Bars Table

8.50 Seed2.0 Pro

1 Seed2.0 Pro 8.50%

#	Model	Score	Setting	Date	Source
1	Seed2.0 Pro	8.50%		Feb 2026	Model card

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card

Labs headline it less often now, last in Feb 2026

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

ByteDance Seed

Date	Launch post	Score	As the post writes it
14 Feb 2026	Seed2.0 Pro	8.5	SWE-Evo

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
14 Feb 2026	Seed2.0 Pro model card	8.5	SWE-Evo (Table 11)	Capabilities

Seed2.0 Pro leads with 8.50%

Scores over time

Labs headline it less often now, last in Feb 2026

One system card reports it

More in Coding