← Back to Leaderboard

SWE-agent

Coding & Software Engineering

#98

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

SWE-agent is an open-source coding & software engineering AI agent maintained by SWE-agent. It ranks #98 on The Agentic Leaderboard with an overall score of 83.1 / 100, scoring 97.4% on reliability and 71.2% on tool selection quality. The project has 20,037 GitHub stars.

Rank
#98
Score
83.1
Category
Coding & Software Engineering
Developer
SWE-agent
Reliability
97.4%
Tool Selection
71.2%
Avg Steps
25
Cost / Task
$0.05
Latency
500ms
GitHub Stars
20k
Mindshare
82.3
View Repository →Share on X

Add this badge to your README

Agentic Leaderboard rank #98
[![Agentic Leaderboard](https://www.theagenticleaderboard.com/badges/swe-agent.svg)](https://www.theagenticleaderboard.com/agent/swe-agent)

Rank history

▼ down 3 this week

21 weeks on the board since Mar 12 · best rank #55

#1#98Mar 11Aug 10

Compared to other Coding & Software Engineering agents