SWE-bench Pro V2
labs.scale.com- Category
- Developer Tools
- Listed in
- Find AI benchmarks
- Type
- TOOL
- Date
About
Repository issue resolution on the public V2 task set from Scale AI and Reflection. Compare task revision, agent harness, execution budget, and grading protocol before comparing results.
Why it made the leaderboard
Compare the task, benchmark version, harness, and grading method before using model scores to choose a model.
Tags
benchmarkevaluation
Media
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.