Organization Card

SWE-bench

We are a team of researchers across Stanford University and Princeton University working on LMs and AI systems for software engineering.

In this organization, you will find the assets for several projects in the SWE-* research ecosystem, notably:

SWE-bench (Lite, Verified, Multimodal, Multilingual)
SWE-smith
SWE-agent

Collections 1

models 3

datasets 7

SWE-bench/SWE-smith

Viewer • Updated 8 days ago • 52.7k • 6.6k • 32

SWE-bench/SWE-smith-trajectories

Viewer • Updated 23 days ago • 76k • 1.34k • 22

SWE-bench/SWE-bench_Verified

Viewer • Updated Apr 29 • 500 • 59.1k • 5

SWE-bench/SWE-bench_Multimodal

Viewer • Updated Apr 29 • 612 • 726 • 5

SWE-bench/SWE-bench_Lite

Viewer • Updated Apr 29 • 323 • 7.64k • 4

SWE-bench/SWE-bench

Viewer • Updated Apr 29 • 21.5k • 1.66k • 7

SWE-bench/SWE-bench_Multilingual

Viewer • Updated Apr 29 • 300 • 15.2k • 2

SWE-bench

AI & ML interests

Recent Activity

SWE-bench

Collections 1

SWE-bench/SWE-bench

SWE-bench/SWE-bench_Lite

SWE-bench/SWE-bench_Verified

SWE-bench/SWE-bench_Multimodal

SWE-bench/SWE-bench

SWE-bench/SWE-bench_Lite

SWE-bench/SWE-bench_Verified

SWE-bench/SWE-bench_Multimodal

models 3

SWE-bench/SWE-agent-LM-7B

SWE-bench/SWE-Rater-32B

SWE-bench/SWE-agent-LM-32B

datasets 7

SWE-bench/SWE-smith

SWE-bench/SWE-smith-trajectories

SWE-bench/SWE-bench_Verified

SWE-bench/SWE-bench_Multimodal

SWE-bench/SWE-bench_Lite

SWE-bench/SWE-bench

SWE-bench/SWE-bench_Multilingual

AI & ML interests

Recent Activity

Team members 5

SWE-bench

Collections 1

models 3 Sort: Recently updated

datasets 7 Sort: Recently updated

models 3

datasets 7