SWE-bench (Lite, Verified, Multimodal, Multilingual) all in one place!
SWE-bench
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
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:
datasets 17
SWE-bench/SWE-prime
Viewer • Updated • 1.36k • 82
SWE-bench/SWE-smith-cpp
Viewer • Updated • 5.12k • 327
SWE-bench/SWE-smith-ts
Viewer • Updated • 5.03k • 327
SWE-bench/SWE-bench_Verified
Benchmark • Updated • 500 • 68.3k • 99
SWE-bench/SWE-smith-java
Viewer • Updated • 7.47k • 411
SWE-bench/SWE-smith-rs
Viewer • Updated • 5.31k • 317 • 2
SWE-bench/SWE-smith-js
Viewer • Updated • 6.07k • 392
SWE-bench/SWE-smith-py
Viewer • Updated • 50.9k • 1.38k • 5
SWE-bench/SWE-smith-go
Viewer • Updated • 8.21k • 474
SWE-bench/SWE-smith-php
Viewer • Updated • 1 • 60